Sham M. Kakade

396 papers A* 124A 8B 4Misc 2Journal 218Unranked 40

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Anytime Pretraining: Horizon-Free Learning-Rate Schedules with Weight Averaging. CoRR Alexandru Meterez, Pranav Ajit Nair, Depen Morwani, Cengiz Pehlevan, Sham M. Kakade
2026	J	`jnl`	Matching Features, Not Tokens: Energy-Based Fine-Tuning of Language Models. CoRR Samy Jelassi, Mujin Kwun, Rosie Zhao, Yuanzhi Li, Nicolò Fusi, Yilun Du, Sham M. Kakade, Carles Domingo-Enrich
2026	J	`jnl`	Prescriptive Scaling Reveals the Evolution of Language Model Capabilities. CoRR Hanlin Zhang, Jikai Jin, Vasilis Syrgkanis, Sham M. Kakade
2026	J	`jnl`	Scaling Reward Modeling without Human Supervision. CoRR Jingxuan Fan, Yueying Li, Zhenting Qi, Dinghuai Zhang, Kianté Brantley, Sham M. Kakade, Hanlin Zhang
2026	J	`jnl`	Stop Training for the Worst: Progressive Unmasking Accelerates Masked Diffusion Training. CoRR Jaeyeon Kim, Jonathan Geuter, David Alvarez-Melis, Sham M. Kakade, Sitan Chen
2025	A*	`conf`	A New Perspective on Shampoo's Preconditioner. ICLR Depen Morwani, Itai Shapira, Nikhil Vyas, Eran Malach, Sham M. Kakade, Lucas Janson
2025	J	`jnl`	A Simplified Analysis of SGD for Linear Regression with Weight Averaging. CoRR Alexandru Meterez, Depen Morwani, Costin-Andrei Oncescu, Jingfeng Wu, Cengiz Pehlevan, Sham M. Kakade
2025	J	`jnl`	Adam or Gauss-Newton? A Comparative Study In Terms of Basis Alignment and SGD Noise. CoRR Bingbin Liu, Rachit Bansal, Depen Morwani, Nikhil Vyas, David Alvarez-Melis, Sham M. Kakade
2025	J	`jnl`	Any-Order Flexible Length Masked Diffusion. CoRR Jaeyeon Kim, Cheuk Kit Lee, Carles Domingo-Enrich, Yilun Du, Sham M. Kakade, Timothy Ngotiaoco, Sitan Chen, Michael S. Albergo
2025	J	`jnl`	Characterization and Mitigation of Training Instabilities in Microscaling Formats. CoRR Huangyuan Su, Mujin Kwun, Stephanie Gil, Sham M. Kakade, Nikhil Anand
2025	J	`jnl`	Connections between Schedule-Free Optimizers, AdEMAMix, and Accelerated SGD Variants. CoRR Depen Morwani, Nikhil Vyas, Hanlin Zhang, Sham M. Kakade
2025	J	`jnl`	Data-Efficient Multi-Agent Spatial Planning with LLMs. CoRR Huangyuan Su, Aaron Walsman, Daniel Garces, Sham M. Kakade, Stephanie Gil
2025	A*	`conf`	Deconstructing What Makes a Good Optimizer for Autoregressive Language Models. ICLR Rosie Zhao, Depen Morwani, David Brandfonbrener, Nikhil Vyas, Sham M. Kakade
2025	J	`jnl`	Discovering Hierarchical Latent Capabilities of Language Models via Causal Representation Learning. CoRR Jikai Jin, Vasilis Syrgkanis, Sham M. Kakade, Hanlin Zhang
2025	J	`jnl`	Distributional Scaling Laws for Emergent Capabilities. CoRR Rosie Zhao, Tian Qin, David Alvarez-Melis, Sham M. Kakade, Naomi Saphra
2025	J	`jnl`	Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretraining. CoRR Rosie Zhao, Alexandru Meterez, Sham M. Kakade, Cengiz Pehlevan, Samy Jelassi, Eran Malach
2025	A*	`conf`	Eliminating Position Bias of Language Models: A Mechanistic Approach. ICLR Ziqi Wang, Hanlin Zhang, Xiner Li, Kuan-Hao Huang, Chi Han, Shuiwang Ji, Sham M. Kakade, Hao Peng, Heng Ji
2025	J	`jnl`	EvoLM: In Search of Lost Language Model Training Dynamics. CoRR Zhenting Qi, Fan Nie, Alexandre Alahi, James Zou, Himabindu Lakkaraju, Yilun Du, Eric P. Xing, Sham M. Kakade, Hanlin Zhang
2025	J	`jnl`	Fine-Tuning Masked Diffusion for Provable Self-Correction. CoRR Jaeyeon Kim, Seunggeun Kim, Taekyun Lee, David Z. Pan, Hyeji Kim, Sham M. Kakade, Sitan Chen
2025	A*	`conf`	Flash Inference: Near Linear Time Inference for Long Convolution Sequence Models and Beyond. ICLR Costin-Andrei Oncescu, Sanket Purandare, Stratos Idreos, Sham M. Kakade
2025	A*	`conf`	Follow My Instruction and Spill the Beans: Scalable Data Extraction from Retrieval-Augmented Generation Systems. ICLR Zhenting Qi, Hanlin Zhang, Eric P. Xing, Sham M. Kakade, Himabindu Lakkaraju
2025	J	`jnl`	GQ-VAE: A gated quantized VAE for learning variable length tokens. CoRR Theo Datta, Kayla Huang, Sham M. Kakade, David Brandfonbrener
2025	A*	`conf`	How Does Critical Batch Size Scale in Pre-training? ICLR Hanlin Zhang, Depen Morwani, Nikhil Vyas, Jingfeng Wu, Difan Zou, Udaya Ghai, Dean P. Foster, Sham M. Kakade
2025	J	`jnl`	In Good GRACEs: Principled Teacher Selection for Knowledge Distillation. CoRR Abhishek Panigrahi, Bingbin Liu, Sadhika Malladi, Sham M. Kakade, Surbhi Goel
2025	J	`jnl`	Inside you are many wolves: Using cognitive models to interpret value trade-offs in LLMs. CoRR Sonia K. Murthy, Rosie Zhao, Jennifer Hu, Sham M. Kakade, Markus Wulfmeier, Peng Qian, Tomer D. Ullman
2025	J	`jnl`	Interpreting the Linear Structure of Vision-language Model Embedding Spaces. CoRR Isabel Papadimitriou, Huangyuan Su, Thomas Fel, Naomi Saphra, Sham M. Kakade, Stephanie Gil
2025	J	`jnl`	LOTION: Smoothing the Optimization Landscape for Quantized Training. CoRR Mujin Kwun, Depen Morwani, Chloe Huangyuan Su, Stephanie Gil, Nikhil Anand, Sham M. Kakade
2025	—	`conf`	LoRA Soups: Merging LoRAs for Practical Skill Composition Tasks. COLING (Industry) Akshara Prabhakar, Yuanzhi Li, Karthik Narasimhan, Sham M. Kakade, Eran Malach, Samy Jelassi
2025	J	`jnl`	Loss-to-Loss Prediction: Scaling Laws for All Datasets. Trans. Mach. Learn. Res. David Brandfonbrener, Nikhil Anand, Nikhil Vyas, Eran Malach, Sham M. Kakade
2025	A*	`conf`	Mind the Gap: Examining the Self-Improvement Capabilities of Large Language Models. ICLR Yuda Song, Hanlin Zhang, Carson Eisenach, Sham M. Kakade, Dean P. Foster, Udaya Ghai
2025	A*	`conf`	Mixture of Parrots: Experts improve memorization more than reasoning. ICLR Samy Jelassi, Clara Mohri, David Brandfonbrener, Alex Gu, Nikhil Vyas, Nikhil Anand, David Alvarez-Melis, Yuanzhi Li, Sham M. Kakade, Eran Malach
2025	J	`jnl`	Risk Comparisons in Linear Regression: Implicit Regularization Dominates Explicit Regularization. CoRR Jingfeng Wu, Peter L. Bartlett, Jason D. Lee, Sham M. Kakade, Bin Yu
2025	A*	`conf`	SOAP: Improving and Stabilizing Shampoo using Adam for Language Modeling. ICLR Nikhil Vyas, Depen Morwani, Rosie Zhao, Itai Shapira, David Brandfonbrener, Lucas Janson, Sham M. Kakade
2025	J	`jnl`	Seesaw: Accelerating Training by Balancing Learning Rate and Batch Size Scheduling. CoRR Alexandru Meterez, Depen Morwani, Jingfeng Wu, Costin-Andrei Oncescu, Cengiz Pehlevan, Sham M. Kakade
2025	J	`jnl`	Selective Underfitting in Diffusion Models. CoRR Kiwhan Song, Jaeyeon Kim, Sitan Chen, Yilun Du, Sham M. Kakade, Vincent Sitzmann
2025	J	`jnl`	Soup to go: mitigating forgetting during continual learning with model averaging. CoRR Anat Kleiman, Gintare Karolina Dziugaite, Jonathan Frankle, Sham M. Kakade, Mansheej Paul
2025	J	`jnl`	The Emergence of Complex Behavior in Large-Scale Ecological Environments. CoRR Joseph Bejjani, Chase Van Amburg, Chengrui Wang, Chloe Huangyuan Su, Sarah M. Pratt, Yasin Mazloumi, Naeem Khoshnevis, Sham M. Kakade, Kianté Brantley, Aaron Walsman
2025	J	`jnl`	The Potential of Second-Order Optimization for LLMs: A Study with Full Gauss-Newton. CoRR Natalie Abreu, Nikhil Vyas, Sham M. Kakade, Depen Morwani
2025	A*	`conf`	The Role of Sparsity for Length Generalization in LLMs. ICML Noah Golowich, Samy Jelassi, David Brandfonbrener, Sham M. Kakade, Eran Malach
2025	J	`jnl`	The Role of Sparsity for Length Generalization in Transformers. CoRR Noah Golowich, Samy Jelassi, David Brandfonbrener, Sham M. Kakade, Eran Malach
2025	A*	`conf`	Train for the Worst, Plan for the Best: Understanding Token Ordering in Masked Diffusions. ICML Jaeyeon Kim, Kulin Shah, Vasilis Kontonis, Sham M. Kakade, Sitan Chen
2025	J	`jnl`	Train for the Worst, Plan for the Best: Understanding Token Ordering in Masked Diffusions. CoRR Jaeyeon Kim, Kulin Shah, Vasilis Kontonis, Sham M. Kakade, Sitan Chen
2025	A*	`conf`	Universal Length Generalization with Turing Programs. ICML Kaiying Hou, David Brandfonbrener, Sham M. Kakade, Samy Jelassi, Eran Malach
2024	J	`jnl`	A New Perspective on Shampoo's Preconditioner. CoRR Depen Morwani, Itai Shapira, Nikhil Vyas, Eran Malach, Sham M. Kakade, Lucas Janson
2024	—	`conf`	A Study on the Calibration of In-context Learning. NAACL-HLT Hanlin Zhang, Yifan Zhang, Yaodong Yu, Dhruv Madeka, Dean P. Foster, Eric P. Xing, Himabindu Lakkaraju, Sham M. Kakade
2024	A*	`conf`	Beyond Implicit Bias: The Insignificance of SGD Noise in Online Learning. ICML Nikhil Vyas, Depen Morwani, Rosie Zhao, Gal Kaplun, Sham M. Kakade, Boaz Barak
2024	A*	`conf`	CoLoR-Filter: Conditional Loss Reduction Filtering for Targeted Language Model Pre-training. NeurIPS David Brandfonbrener, Hanlin Zhang, Andreas Kirsch, Jonathan Richard Schwarz, Sham M. Kakade
2024	J	`jnl`	CoLoR-Filter: Conditional Loss Reduction Filtering for Targeted Language Model Pre-training. CoRR David Brandfonbrener, Hanlin Zhang, Andreas Kirsch, Jonathan Richard Schwarz, Sham M. Kakade
2024	A*	`conf`	DataComp-LM: In search of the next generation of training sets for language models. NeurIPS Jeffrey Li, Alex Fang, Georgios Smyrnis, Maor Ivgi, Matt Jordan, Samir Yitzhak Gadre, Hritik Bansal, Etash Kumar Guha, Sedrick Scott Keh, Kushal Arora, Saurabh Garg, Rui Xin, Niklas Muennighoff, Reinhard Heckel, Jean Mercat, Mayee F. Chen, Suchin Gururangan, Mitchell Wortsman, Alon Albalak, Yonatan Bitton, Marianna Nezhurina, Amro Abbas, Cheng-Yu Hsieh, Dhruba Ghosh, Josh Gardner, Maciej Kilian, Hanlin Zhang, Rulin Shao, Sarah M. Pratt, Sunny Sanyal, Gabriel Ilharco, Giannis Daras, Kalyani Marathe, Aaron Gokaslan, Jieyu Zhang, Khyathi Raghavi Chandu, Thao Nguyen, Igor Vasiljevic, Sham M. Kakade, Shuran Song, Sujay Sanghavi, Fartash Faghri, Sewoong Oh, Luke Zettlemoyer, Kyle Lo, Alaaeldin El-Nouby, Hadi Pouransari, Alexander Toshev, Stephanie Wang, Dirk Groeneveld, Luca Soldaini, Pang Wei Koh, Jenia Jitsev, Thomas Kollar, Alex Dimakis, Yair Carmon, Achal Dave, Ludwig Schmidt, Vaishaal Shankar
2024	J	`jnl`	DataComp-LM: In search of the next generation of training sets for language models. CoRR Jeffrey Li, Alex Fang, Georgios Smyrnis, Maor Ivgi, Matt Jordan, Samir Yitzhak Gadre, Hritik Bansal, Etash Kumar Guha, Sedrick Keh, Kushal Arora, Saurabh Garg, Rui Xin, Niklas Muennighoff, Reinhard Heckel, Jean Mercat, Mayee F. Chen, Suchin Gururangan, Mitchell Wortsman, Alon Albalak, Yonatan Bitton, Marianna Nezhurina, Amro Abbas, Cheng-Yu Hsieh, Dhruba Ghosh, Josh Gardner, Maciej Kilian, Hanlin Zhang, Rulin Shao, Sarah M. Pratt, Sunny Sanyal, Gabriel Ilharco, Giannis Daras, Kalyani Marathe, Aaron Gokaslan, Jieyu Zhang, Khyathi Raghavi Chandu, Thao Nguyen, Igor Vasiljevic, Sham M. Kakade, Shuran Song, Sujay Sanghavi, Fartash Faghri, Sewoong Oh, Luke Zettlemoyer, Kyle Lo, Alaaeldin El-Nouby, Hadi Pouransari, Alexander Toshev, Stephanie Wang, Dirk Groeneveld, Luca Soldaini, Pang Wei Koh, Jenia Jitsev, Thomas Kollar, Alexandros G. Dimakis, Yair Carmon, Achal Dave, Ludwig Schmidt, Vaishaal Shankar
2024	J	`jnl`	Deconstructing What Makes a Good Optimizer for Language Models. CoRR Rosie Zhao, Depen Morwani, David Brandfonbrener, Nikhil Vyas, Sham M. Kakade
2024	J	`jnl`	Eliminating Position Bias of Language Models: A Mechanistic Approach. CoRR Ziqi Wang, Hanlin Zhang, Xiner Li, Kuan-Hao Huang, Chi Han, Shuiwang Ji, Sham M. Kakade, Hao Peng, Heng Ji
2024	A*	`conf`	Feature emergence via margin maximization: case studies in algebraic tasks. ICLR Depen Morwani, Benjamin L. Edelman, Costin-Andrei Oncescu, Rosie Zhao, Sham M. Kakade
2024	J	`jnl`	Flash Inference: Near Linear Time Inference for Long Convolution Sequence Models and Beyond. CoRR Costin-Andrei Oncescu, Sanket Purandare, Stratos Idreos, Sham M. Kakade
2024	J	`jnl`	Follow My Instruction and Spill the Beans: Scalable Data Extraction from Retrieval-Augmented Generation Systems. CoRR Zhenting Qi, Hanlin Zhang, Eric P. Xing, Sham M. Kakade, Himabindu Lakkaraju
2024	J	`jnl`	From an Image to a Scene: Learning to Imagine the World from a Million 360 Videos. CoRR Matthew Wallingford, Anand Bhattad, Aditya Kusupati, Vivek Ramanujan, Matt Deitke, Sham M. Kakade, Aniruddha Kembhavi, Roozbeh Mottaghi, Wei-Chiu Ma, Ali Farhadi
2024	J	`jnl`	How Does Critical Batch Size Scale in Pre-training? CoRR Hanlin Zhang, Depen Morwani, Nikhil Vyas, Jingfeng Wu, Difan Zou, Udaya Ghai, Dean P. Foster, Sham M. Kakade
2024	J	`jnl`	Koopman Spectrum Nonlinear Regulators and Efficient Online Learning. Trans. Mach. Learn. Res. Motoya Ohnishi, Isao Ishikawa, Kendall Lowrey, Masahiro Ikeda, Sham M. Kakade, Yoshinobu Kawahara
2024	J	`jnl`	LoRA Soups: Merging LoRAs for Practical Skill Composition Tasks. CoRR Akshara Prabhakar, Yuanzhi Li, Karthik Narasimhan, Sham M. Kakade, Eran Malach, Samy Jelassi
2024	J	`jnl`	Loss-to-Loss Prediction: Scaling Laws for All Datasets. CoRR David Brandfonbrener, Nikhil Anand, Nikhil Vyas, Eran Malach, Sham M. Kakade
2024	A*	`conf`	MatFormer: Nested Transformer for Elastic Inference. NeurIPS Devvrit, Sneha Kudugunta, Aditya Kusupati, Tim Dettmers, Kaifeng Chen, Inderjit S. Dhillon, Yulia Tsvetkov, Hanna Hajishirzi, Sham M. Kakade, Ali Farhadi, Prateek Jain
2024	A*	`conf`	Matching the Statistical Query Lower Bound for k-Sparse Parity Problems with Sign Stochastic Gradient Descent. NeurIPS Yiwen Kou, Zixiang Chen, Quanquan Gu, Sham M. Kakade
2024	J	`jnl`	Matching the Statistical Query Lower Bound for k-sparse Parity Problems with Stochastic Gradient Descent. CoRR Yiwen Kou, Zixiang Chen, Quanquan Gu, Sham M. Kakade
2024	J	`jnl`	Mind the Gap: Examining the Self-Improvement Capabilities of Large Language Models. CoRR Yuda Song, Hanlin Zhang, Carson Eisenach, Sham M. Kakade, Dean P. Foster, Udaya Ghai
2024	J	`jnl`	Mixture of Parrots: Experts improve memorization more than reasoning. CoRR Samy Jelassi, Clara Mohri, David Brandfonbrener, Alex Gu, Nikhil Vyas, Nikhil Anand, David Alvarez-Melis, Yuanzhi Li, Sham M. Kakade, Eran Malach
2024	J	`jnl`	Multi-Agent Reinforcement Learning from Human Feedback: Data Coverage and Algorithmic Techniques. CoRR Natalia Zhang, Xinqi Wang, Qiwen Cui, Runlong Zhou, Sham M. Kakade, Simon S. Du
2024	J	`jnl`	Neural Coordination and Capacity Control for Inventory Management. CoRR Carson Eisenach, Udaya Ghai, Dhruv Madeka, Kari Torkkola, Dean P. Foster, Sham M. Kakade
2024	A*	`conf`	Q-Probe: A Lightweight Approach to Reward Maximization for Language Models. ICML Kenneth Li, Samy Jelassi, Hugh Zhang, Sham M. Kakade, Martin Wattenberg, David Brandfonbrener
2024	J	`jnl`	Q-Probe: A Lightweight Approach to Reward Maximization for Language Models. CoRR Kenneth Li, Samy Jelassi, Hugh Zhang, Sham M. Kakade, Martin Wattenberg, David Brandfonbrener
2024	A*	`conf`	Repeat After Me: Transformers are Better than State Space Models at Copying. ICML Samy Jelassi, David Brandfonbrener, Sham M. Kakade, Eran Malach
2024	J	`jnl`	Repeat After Me: Transformers are Better than State Space Models at Copying. CoRR Samy Jelassi, David Brandfonbrener, Sham M. Kakade, Eran Malach
2024	J	`jnl`	SOAP: Improving and Stabilizing Shampoo using Adam. CoRR Nikhil Vyas, Depen Morwani, Rosie Zhao, Itai Shapira, David Brandfonbrener, Lucas Janson, Sham M. Kakade
2024	J	`jnl`	Scaling Laws for Imitation Learning in Single-Agent Games. Trans. Mach. Learn. Res. Jens Tuyls, Dhruv Madeka, Kari Torkkola, Dean P. Foster, Karthik R. Narasimhan, Sham M. Kakade
2024	A*	`conf`	Scaling Laws in Linear Regression: Compute, Parameters, and Data. NeurIPS Licong Lin, Jingfeng Wu, Sham M. Kakade, Peter L. Bartlett, Jason D. Lee
2024	J	`jnl`	Scaling Laws in Linear Regression: Compute, Parameters, and Data. CoRR Licong Lin, Jingfeng Wu, Sham M. Kakade, Peter L. Bartlett, Jason D. Lee
2024	A*	`conf`	Superposed Decoding: Multiple Generations from a Single Autoregressive Inference Pass. NeurIPS Ethan Shen, Alan Fan, Sarah M. Pratt, Jae Sung Park, Matthew Wallingford, Sham M. Kakade, Ari Holtzman, Ranjay Krishna, Ali Farhadi, Aditya Kusupati
2024	J	`jnl`	Superposed Decoding: Multiple Generations from a Single Autoregressive Inference Pass. CoRR Ethan Shen, Alan Fan, Sarah M. Pratt, Jae Sung Park, Matthew Wallingford, Sham M. Kakade, Ari Holtzman, Ranjay Krishna, Ali Farhadi, Aditya Kusupati
2024	A*	`conf`	Transcendence: Generative Models Can Outperform The Experts That Train Them. NeurIPS Edwin Zhang, Vincent Zhu, Naomi Saphra, Anat Kleiman, Benjamin L. Edelman, Milind Tambe, Sham M. Kakade, Eran Malach
2024	J	`jnl`	Transcendence: Generative Models Can Outperform The Experts That Train Them. CoRR Edwin Zhang, Vincent Zhu, Naomi Saphra, Anat Kleiman, Benjamin L. Edelman, Milind Tambe, Sham M. Kakade, Eran Malach
2024	J	`jnl`	Universal Length Generalization with Turing Programs. CoRR Kaiying Hou, David Brandfonbrener, Sham M. Kakade, Samy Jelassi, Eran Malach
2023	J	`jnl`	A Complete Characterization of Linear Estimators for Offline Policy Evaluation. J. Mach. Learn. Res. Juan C. Perdomo, Akshay Krishnamurthy, Peter L. Bartlett, Sham M. Kakade
2023	J	`jnl`	A Study on the Calibration of In-context Learning. CoRR Hanlin Zhang, Yifan Zhang, Yaodong Yu, Dhruv Madeka, Dean P. Foster, Eric P. Xing, Himabindu Lakkaraju, Sham M. Kakade
2023	A*	`conf`	AdANNS: A Framework for Adaptive Semantic Search. NeurIPS Aniket Rege, Aditya Kusupati, Sharan Ranjit S, Alan Fan, Qingqing Cao, Sham M. Kakade, Prateek Jain, Ali Farhadi
2023	J	`jnl`	AdANNS: A Framework for Adaptive Semantic Search. CoRR Aniket Rege, Aditya Kusupati, Sharan Ranjit S, Alan Fan, Qingqing Cao, Sham M. Kakade, Prateek Jain, Ali Farhadi
2023	J	`jnl`	Benign Overfitting of Constant-Stepsize SGD for Linear Regression. J. Mach. Learn. Res. Difan Zou, Jingfeng Wu, Vladimir Braverman, Quanquan Gu, Sham M. Kakade
2023	J	`jnl`	Beyond Implicit Bias: The Insignificance of SGD Noise in Online Learning. CoRR Nikhil Vyas, Depen Morwani, Rosie Zhao, Gal Kaplun, Sham M. Kakade, Boaz Barak
2023	J	`jnl`	Feature emergence via margin maximization: case studies in algebraic tasks. CoRR Depen Morwani, Benjamin L. Edelman, Costin-Andrei Oncescu, Rosie Zhao, Sham M. Kakade
2023	A*	`conf`	Finite-Sample Analysis of Learning High-Dimensional Single ReLU Neuron. ICML Jingfeng Wu, Difan Zou, Zixiang Chen, Vladimir Braverman, Quanquan Gu, Sham M. Kakade
2023	A*	`conf`	Hardness of Independent Learning and Sparse Equilibrium Computation in Markov Games. ICML Dylan J. Foster, Noah Golowich, Sham M. Kakade
2023	J	`jnl`	Hardness of Independent Learning and Sparse Equilibrium Computation in Markov Games. CoRR Dylan J. Foster, Noah Golowich, Sham M. Kakade
2023	A*	`conf`	Learning Hidden Markov Models Using Conditional Samples. COLT Gaurav Mahajan, Sham M. Kakade, Akshay Krishnamurthy, Cyril Zhang
2023	J	`jnl`	Learning Hidden Markov Models Using Conditional Samples. CoRR Sham M. Kakade, Akshay Krishnamurthy, Gaurav Mahajan, Cyril Zhang
2023	J	`jnl`	Learning High-Dimensional Single-Neuron ReLU Networks with Finite Samples. CoRR Jingfeng Wu, Difan Zou, Zixiang Chen, Vladimir Braverman, Quanquan Gu, Sham M. Kakade
2023	J	`jnl`	Learning an Inventory Control Policy with General Inventory Arrival Dynamics. CoRR Sohrab Andaz, Carson Eisenach, Dhruv Madeka, Kari Torkkola, Randy Jia, Dean P. Foster, Sham M. Kakade
2023	J	`jnl`	MatFormer: Nested Transformer for Elastic Inference. CoRR Devvrit, Sneha Kudugunta, Aditya Kusupati, Tim Dettmers, Kaifeng Chen, Inderjit S. Dhillon, Yulia Tsvetkov, Hannaneh Hajishirzi, Sham M. Kakade, Ali Farhadi, Prateek Jain
2023	J	`jnl`	Model-Based Multi-Agent RL in Zero-Sum Markov Games with Near-Optimal Sample Complexity. J. Mach. Learn. Res. Kaiqing Zhang, Sham M. Kakade, Tamer Basar, Lin F. Yang
2023	—	`conf`	Modified Gauss-Newton Algorithms under Noise. SSP Krishna Pillutla, Vincent Roulet, Sham M. Kakade, Zaïd Harchaoui
2023	J	`jnl`	Modified Gauss-Newton Algorithms under Noise. CoRR Krishna Pillutla, Vincent Roulet, Sham M. Kakade, Zaïd Harchaoui
2023	A*	`conf`	On Provable Copyright Protection for Generative Models. ICML Nikhil Vyas, Sham M. Kakade, Boaz Barak
2023	A*	`conf`	Pareto Frontiers in Deep Feature Learning: Data, Compute, Width, and Luck. NeurIPS Benjamin L. Edelman, Surbhi Goel, Sham M. Kakade, Eran Malach, Cyril Zhang
2023	J	`jnl`	Pareto Frontiers in Neural Feature Learning: Data, Compute, Width, and Luck. CoRR Benjamin L. Edelman, Surbhi Goel, Sham M. Kakade, Eran Malach, Cyril Zhang
2023	J	`jnl`	Provable Copyright Protection for Generative Models. CoRR Nikhil Vyas, Sham M. Kakade, Boaz Barak
2023	J	`jnl`	Scaling Laws for Imitation Learning in NetHack. CoRR Jens Tuyls, Dhruv Madeka, Kari Torkkola, Dean P. Foster, Karthik Narasimhan, Sham M. Kakade
2023	A*	`conf`	The Role of Coverage in Online Reinforcement Learning. ICLR Tengyang Xie, Dylan J. Foster, Yu Bai, Nan Jiang, Sham M. Kakade
2022	J	`jnl`	A Sharp Characterization of Linear Estimators for Offline Policy Evaluation. CoRR Juan C. Perdomo, Akshay Krishnamurthy, Peter L. Bartlett, Sham M. Kakade
2022	A*	`conf`	Anti-Concentrated Confidence Bonuses For Scalable Exploration. ICLR Jordan T. Ash, Cyril Zhang, Surbhi Goel, Akshay Krishnamurthy, Sham M. Kakade
2022	A*	`conf`	Hidden Progress in Deep Learning: SGD Learns Parities Near the Computational Limit. NeurIPS Boaz Barak, Benjamin L. Edelman, Surbhi Goel, Sham M. Kakade, Eran Malach, Cyril Zhang
2022	J	`jnl`	Hidden Progress in Deep Learning: SGD Learns Parities Near the Computational Limit. CoRR Boaz Barak, Benjamin L. Edelman, Surbhi Goel, Sham M. Kakade, Eran Malach, Cyril Zhang
2022	A*	`conf`	Inductive Biases and Variable Creation in Self-Attention Mechanisms. ICML Benjamin L. Edelman, Surbhi Goel, Sham M. Kakade, Cyril Zhang
2022	A*	`conf`	Last Iterate Risk Bounds of SGD with Decaying Stepsize for Overparameterized Linear Regression. ICML Jingfeng Wu, Difan Zou, Vladimir Braverman, Quanquan Gu, Sham M. Kakade
2022	A*	`conf`	Matryoshka Representation Learning. NeurIPS Aditya Kusupati, Gantavya Bhatt, Aniket Rege, Matthew Wallingford, Aditya Sinha, Vivek Ramanujan, William Howard-Snyder, Kaifeng Chen, Sham M. Kakade, Prateek Jain, Ali Farhadi
2022	J	`jnl`	Matryoshka Representations for Adaptive Deployment. CoRR Aditya Kusupati, Gantavya Bhatt, Aniket Rege, Matthew Wallingford, Aditya Sinha, Vivek Ramanujan, William Howard-Snyder, Kaifeng Chen, Sham M. Kakade, Prateek Jain, Ali Farhadi
2022	A*	`conf`	Multi-Stage Episodic Control for Strategic Exploration in Text Games. ICLR Jens Tuyls, Shunyu Yao, Sham M. Kakade, Karthik Narasimhan
2022	J	`jnl`	Multi-Stage Episodic Control for Strategic Exploration in Text Games. CoRR Jens Tuyls, Shunyu Yao, Sham M. Kakade, Karthik Narasimhan
2022	A*	`conf`	Recurrent Convolutional Neural Networks Learn Succinct Learning Algorithms. NeurIPS Surbhi Goel, Sham M. Kakade, Adam Kalai, Cyril Zhang
2022	J	`jnl`	Recurrent Convolutional Neural Networks Learn Succinct Learning Algorithms. CoRR Surbhi Goel, Sham M. Kakade, Adam Tauman Kalai, Cyril Zhang
2022	A*	`conf`	Risk Bounds of Multi-Pass SGD for Least Squares in the Interpolation Regime. NeurIPS Difan Zou, Jingfeng Wu, Vladimir Braverman, Quanquan Gu, Sham M. Kakade
2022	J	`jnl`	Risk Bounds of Multi-Pass SGD for Least Squares in the Interpolation Regime. CoRR Difan Zou, Jingfeng Wu, Vladimir Braverman, Quanquan Gu, Sham M. Kakade
2022	J	`jnl`	Robust Aggregation for Federated Learning. IEEE Trans. Signal Process. Krishna Pillutla, Sham M. Kakade, Zaïd Harchaoui
2022	A*	`conf`	Sparsity in Partially Controllable Linear Systems. ICML Yonathan Efroni, Sham M. Kakade, Akshay Krishnamurthy, Cyril Zhang
2022	A*	`conf`	The Power and Limitation of Pretraining-Finetuning for Linear Regression under Covariate Shift. NeurIPS Jingfeng Wu, Difan Zou, Vladimir Braverman, Quanquan Gu, Sham M. Kakade
2022	J	`jnl`	The Power and Limitation of Pretraining-Finetuning for Linear Regression under Covariate Shift. CoRR Jingfeng Wu, Difan Zou, Vladimir Braverman, Quanquan Gu, Sham M. Kakade
2022	J	`jnl`	The Role of Coverage in Online Reinforcement Learning. CoRR Tengyang Xie, Dylan J. Foster, Yu Bai, Nan Jiang, Sham M. Kakade
2022	A*	`conf`	Understanding Contrastive Learning Requires Incorporating Inductive Biases. ICML Nikunj Saunshi, Jordan T. Ash, Surbhi Goel, Dipendra Misra, Cyril Zhang, Sanjeev Arora, Sham M. Kakade, Akshay Krishnamurthy
2022	J	`jnl`	Understanding Contrastive Learning Requires Incorporating Inductive Biases. CoRR Nikunj Saunshi, Jordan T. Ash, Surbhi Goel, Dipendra Misra, Cyril Zhang, Sanjeev Arora, Sham M. Kakade, Akshay Krishnamurthy
2022	A*	`conf`	Unpacking Reward Shaping: Understanding the Benefits of Reward Engineering on Sample Complexity. NeurIPS Abhishek Gupta, Aldo Pacchiano, Yuexiang Zhai, Sham M. Kakade, Sergey Levine
2022	J	`jnl`	Unpacking Reward Shaping: Understanding the Benefits of Reward Engineering on Sample Complexity. CoRR Abhishek Gupta, Aldo Pacchiano, Yuexiang Zhai, Sham M. Kakade, Sergey Levine
2021	J	`jnl`	A Short Note on the Relationship of Information Gain and Eluder Dimension. CoRR Kaixuan Huang, Sham M. Kakade, Jason D. Lee, Qi Lei
2021	A*	`conf`	An Exponential Lower Bound for Linearly Realizable MDP with Constant Suboptimality Gap. NeurIPS Yuanhao Wang, Ruosong Wang, Sham M. Kakade
2021	J	`jnl`	An Exponential Lower Bound for Linearly-Realizable MDPs with Constant Suboptimality Gap. CoRR Yuanhao Wang, Ruosong Wang, Sham M. Kakade
2021	J	`jnl`	Anti-Concentrated Confidence Bonuses for Scalable Exploration. CoRR Jordan T. Ash, Cyril Zhang, Surbhi Goel, Akshay Krishnamurthy, Sham M. Kakade
2021	A*	`conf`	Benign Overfitting of Constant-Stepsize SGD for Linear Regression. COLT Difan Zou, Jingfeng Wu, Vladimir Braverman, Quanquan Gu, Sham M. Kakade
2021	J	`jnl`	Benign Overfitting of Constant-Stepsize SGD for Linear Regression. CoRR Difan Zou, Jingfeng Wu, Vladimir Braverman, Quanquan Gu, Sham M. Kakade
2021	A*	`conf`	Bilinear Classes: A Structural Framework for Provable Generalization in RL. ICML Simon S. Du, Sham M. Kakade, Jason D. Lee, Shachar Lovett, Gaurav Mahajan, Wen Sun, Ruosong Wang
2021	J	`jnl`	Bilinear Classes: A Structural Framework for Provable Generalization in RL. CoRR Simon S. Du, Sham M. Kakade, Jason D. Lee, Shachar Lovett, Gaurav Mahajan, Wen Sun, Ruosong Wang
2021	A*	`conf`	Few-Shot Learning via Learning the Representation, Provably. ICLR Simon Shaolei Du, Wei Hu, Sham M. Kakade, Jason D. Lee, Qi Lei
2021	A*	`conf`	Going Beyond Linear RL: Sample Efficient Neural Function Approximation. NeurIPS Baihe Huang, Kaixuan Huang, Sham M. Kakade, Jason D. Lee, Qi Lei, Runzhe Wang, Jiaqi Yang
2021	J	`jnl`	Going Beyond Linear RL: Sample Efficient Neural Function Approximation. CoRR Baihe Huang, Kaixuan Huang, Sham M. Kakade, Jason D. Lee, Qi Lei, Runzhe Wang, Jiaqi Yang
2021	A*	`conf`	Gone Fishing: Neural Active Learning with Fisher Embeddings. NeurIPS Jordan T. Ash, Surbhi Goel, Akshay Krishnamurthy, Sham M. Kakade
2021	J	`jnl`	Gone Fishing: Neural Active Learning with Fisher Embeddings. CoRR Jordan T. Ash, Surbhi Goel, Akshay Krishnamurthy, Sham M. Kakade
2021	A*	`conf`	How Important is the Train-Validation Split in Meta-Learning? ICML Yu Bai, Minshuo Chen, Pan Zhou, Tuo Zhao, Jason D. Lee, Sham M. Kakade, Huan Wang, Caiming Xiong
2021	J	`jnl`	Inductive Biases and Variable Creation in Self-Attention Mechanisms. CoRR Benjamin L. Edelman, Surbhi Goel, Sham M. Kakade, Cyril Zhang
2021	A*	`conf`	Instabilities of Offline RL with Pre-Trained Neural Representation. ICML Ruosong Wang, Yifan Wu, Ruslan Salakhutdinov, Sham M. Kakade
2021	J	`jnl`	Instabilities of Offline RL with Pre-Trained Neural Representation. CoRR Ruosong Wang, Yifan Wu, Ruslan Salakhutdinov, Sham M. Kakade
2021	J	`jnl`	Koopman Spectrum Nonlinear Regulator and Provably Efficient Online Learning. CoRR Motoya Ohnishi, Isao Ishikawa, Kendall Lowrey, Masahiro Ikeda, Sham M. Kakade, Yoshinobu Kawahara
2021	A*	`conf`	LLC: Accurate, Multi-purpose Learnt Low-dimensional Binary Codes. NeurIPS Aditya Kusupati, Matthew Wallingford, Vivek Ramanujan, Raghav Somani, Jae Sung Park, Krishna Pillutla, Prateek Jain, Sham M. Kakade, Ali Farhadi
2021	J	`jnl`	LLC: Accurate, Multi-purpose Learnt Low-dimensional Binary Codes. CoRR Aditya Kusupati, Matthew Wallingford, Vivek Ramanujan, Raghav Somani, Jae Sung Park, Krishna Pillutla, Prateek Jain, Sham M. Kakade, Ali Farhadi
2021	J	`jnl`	Last Iterate Risk Bounds of SGD with Decaying Stepsize for Overparameterized Linear Regression. CoRR Jingfeng Wu, Difan Zou, Vladimir Braverman, Quanquan Gu, Sham M. Kakade
2021	J	`jnl`	On Nonconvex Optimization for Machine Learning: Gradients, Stochasticity, and Saddle Points. J. ACM Chi Jin, Praneeth Netrapalli, Rong Ge, Sham M. Kakade, Michael I. Jordan
2021	J	`jnl`	On the Theory of Policy Gradient Methods: Optimality, Approximation, and Distribution Shift. J. Mach. Learn. Res. Alekh Agarwal, Sham M. Kakade, Jason D. Lee, Gaurav Mahajan
2021	A*	`conf`	Optimal Gradient-based Algorithms for Non-concave Bandit Optimization. NeurIPS Baihe Huang, Kaixuan Huang, Sham M. Kakade, Jason D. Lee, Qi Lei, Runzhe Wang, Jiaqi Yang
2021	J	`jnl`	Optimal Gradient-based Algorithms for Non-concave Bandit Optimization. CoRR Baihe Huang, Kaixuan Huang, Sham M. Kakade, Jason D. Lee, Qi Lei, Runzhe Wang, Jiaqi Yang
2021	A*	`conf`	Optimal Regularization can Mitigate Double Descent. ICLR Preetum Nakkiran, Prayaag Venkat, Sham M. Kakade, Tengyu Ma
2021	J	`jnl`	Robust and Differentially Private Mean Estimation. CoRR Xiyang Liu, Weihao Kong, Sham M. Kakade, Sewoong Oh
2021	A*	`conf`	Robust and differentially private mean estimation. NeurIPS Xiyang Liu, Weihao Kong, Sham M. Kakade, Sewoong Oh
2021	J	`jnl`	Sparsity in Partially Controllable Linear Systems. CoRR Yonathan Efroni, Sham M. Kakade, Akshay Krishnamurthy, Cyril Zhang
2021	A*	`conf`	The Benefits of Implicit Regularization from SGD in Least Squares Problems. NeurIPS Difan Zou, Jingfeng Wu, Vladimir Braverman, Quanquan Gu, Dean P. Foster, Sham M. Kakade
2021	J	`jnl`	The Benefits of Implicit Regularization from SGD in Least Squares Problems. CoRR Difan Zou, Jingfeng Wu, Vladimir Braverman, Quanquan Gu, Dean P. Foster, Sham M. Kakade
2021	J	`jnl`	The Statistical Complexity of Interactive Decision Making. CoRR Dylan J. Foster, Sham M. Kakade, Jian Qian, Alexander Rakhlin
2021	A*	`conf`	What are the Statistical Limits of Offline RL with Linear Function Approximation? ICLR Ruosong Wang, Dean P. Foster, Sham M. Kakade
2020	A*	`conf`	Calibration, Entropy Rates, and Memory in Language Models. ICML Mark Braverman, Xinyi Chen, Sham M. Kakade, Karthik Narasimhan, Cyril Zhang, Yi Zhang
2020	A*	`conf`	FLAMBE: Structural Complexity and Representation Learning of Low Rank MDPs. NeurIPS Alekh Agarwal, Sham M. Kakade, Akshay Krishnamurthy, Wen Sun
2020	J	`jnl`	FLAMBE: Structural Complexity and Representation Learning of Low Rank MDPs. CoRR Alekh Agarwal, Sham M. Kakade, Akshay Krishnamurthy, Wen Sun
2020	J	`jnl`	Few-Shot Learning via Learning the Representation, Provably. CoRR Simon S. Du, Wei Hu, Sham M. Kakade, Jason D. Lee, Qi Lei
2020	J	`jnl`	How Important is the Train-Validation Split in Meta-Learning? CoRR Yu Bai, Minshuo Chen, Pan Zhou, Tuo Zhao, Jason D. Lee, Sham M. Kakade, Huan Wang, Caiming Xiong
2020	A*	`conf`	Information Theoretic Regret Bounds for Online Nonlinear Control. NeurIPS Sham M. Kakade, Akshay Krishnamurthy, Kendall Lowrey, Motoya Ohnishi, Wen Sun
2020	J	`jnl`	Information Theoretic Regret Bounds for Online Nonlinear Control. CoRR Sham M. Kakade, Akshay Krishnamurthy, Kendall Lowrey, Motoya Ohnishi, Wen Sun
2020	A*	`conf`	Is Long Horizon RL More Difficult Than Short Horizon RL? NeurIPS Ruosong Wang, Simon S. Du, Lin F. Yang, Sham M. Kakade
2020	J	`jnl`	Is Long Horizon Reinforcement Learning More Difficult Than Short Horizon Reinforcement Learning? CoRR Ruosong Wang, Simon S. Du, Lin F. Yang, Sham M. Kakade
2020	A*	`conf`	Is a Good Representation Sufficient for Sample Efficient Reinforcement Learning? ICLR Simon S. Du, Sham M. Kakade, Ruosong Wang, Lin F. Yang
2020	B	`conf`	Leverage Score Sampling for Faster Accelerated Regression and ERM. ALT Naman Agarwal, Sham M. Kakade, Rahul Kidambi, Yin Tat Lee, Praneeth Netrapalli, Aaron Sidford
2020	A*	`conf`	Meta-learning for Mixed Linear Regression. ICML Weihao Kong, Raghav Somani, Zhao Song, Sham M. Kakade, Sewoong Oh
2020	J	`jnl`	Meta-learning for mixed linear regression. CoRR Weihao Kong, Raghav Somani, Zhao Song, Sham M. Kakade, Sewoong Oh
2020	A*	`conf`	Model-Based Multi-Agent RL in Zero-Sum Markov Games with Near-Optimal Sample Complexity. NeurIPS Kaiqing Zhang, Sham M. Kakade, Tamer Basar, Lin F. Yang
2020	J	`jnl`	Model-Based Multi-Agent RL in Zero-Sum Markov Games with Near-Optimal Sample Complexity. CoRR Kaiqing Zhang, Sham M. Kakade, Tamer Basar, Lin F. Yang
2020	A*	`conf`	Model-Based Reinforcement Learning with a Generative Model is Minimax Optimal. COLT Alekh Agarwal, Sham M. Kakade, Lin F. Yang
2020	J	`jnl`	Optimal Regularization Can Mitigate Double Descent. CoRR Preetum Nakkiran, Prayaag Venkat, Sham M. Kakade, Tengyu Ma
2020	A*	`conf`	Optimality and Approximation with Policy Gradient Methods in Markov Decision Processes. COLT Alekh Agarwal, Sham M. Kakade, Jason D. Lee, Gaurav Mahajan
2020	J	`jnl`	PACT: Privacy Sensitive Protocols and Mechanisms for Mobile Contact Tracing. CoRR Justin Chan, Dean P. Foster, Shyam Gollakota, Eric Horvitz, Joseph Jaeger, Sham M. Kakade, Tadayoshi Kohno, John Langford, Jonathan Larson, Sudheesh Singanamalla, Jacob E. Sunshine, Stefano Tessaro
2020	J	`jnl`	PACT: Privacy-Sensitive Protocols And Mechanisms for Mobile Contact Tracing. IEEE Data Eng. Bull. Justin Chan, Landon P. Cox, Dean P. Foster, Shyam Gollakota, Eric Horvitz, Joseph Jaeger, Sham M. Kakade, Tadayoshi Kohno, John Langford, Jonathan Larson, Puneet Sharma, Sudheesh Singanamalla, Jacob E. Sunshine, Stefano Tessaro
2020	A*	`conf`	PC-PG: Policy Cover Directed Exploration for Provable Policy Gradient Learning. NeurIPS Alekh Agarwal, Mikael Henaff, Sham M. Kakade, Wen Sun
2020	J	`jnl`	PC-PG: Policy Cover Directed Exploration for Provable Policy Gradient Learning. CoRR Alekh Agarwal, Mikael Henaff, Sham M. Kakade, Wen Sun
2020	A*	`conf`	Provable Representation Learning for Imitation Learning via Bi-level Optimization. ICML Sanjeev Arora, Simon S. Du, Sham M. Kakade, Yuping Luo, Nikunj Saunshi
2020	J	`jnl`	Provable Representation Learning for Imitation Learning via Bi-level Optimization. CoRR Sanjeev Arora, Simon S. Du, Sham M. Kakade, Yuping Luo, Nikunj Saunshi
2020	A*	`conf`	Robust Meta-learning for Mixed Linear Regression with Small Batches. NeurIPS Weihao Kong, Raghav Somani, Sham M. Kakade, Sewoong Oh
2020	J	`jnl`	Robust Meta-learning for Mixed Linear Regression with Small Batches. CoRR Weihao Kong, Raghav Somani, Sham M. Kakade, Sewoong Oh
2020	A*	`conf`	Sample-Efficient Reinforcement Learning of Undercomplete POMDPs. NeurIPS Chi Jin, Sham M. Kakade, Akshay Krishnamurthy, Qinghua Liu
2020	J	`jnl`	Sample-Efficient Reinforcement Learning of Undercomplete POMDPs. CoRR Chi Jin, Sham M. Kakade, Akshay Krishnamurthy, Qinghua Liu
2020	A*	`conf`	Soft Threshold Weight Reparameterization for Learnable Sparsity. ICML Aditya Kusupati, Vivek Ramanujan, Raghav Somani, Mitchell Wortsman, Prateek Jain, Sham M. Kakade, Ali Farhadi
2020	J	`jnl`	Soft Threshold Weight Reparameterization for Learnable Sparsity. CoRR Aditya Kusupati, Vivek Ramanujan, Raghav Somani, Mitchell Wortsman, Prateek Jain, Sham M. Kakade, Ali Farhadi
2020	J	`jnl`	Stochastic Subgradient Method Converges on Tame Functions. Found. Comput. Math. Damek Davis, Dmitriy Drusvyatskiy, Sham M. Kakade, Jason D. Lee
2020	A*	`conf`	The Implicit and Explicit Regularization Effects of Dropout. ICML Colin Wei, Sham M. Kakade, Tengyu Ma
2020	J	`jnl`	The Implicit and Explicit Regularization Effects of Dropout. CoRR Colin Wei, Sham M. Kakade, Tengyu Ma
2020	B	`conf`	The Nonstochastic Control Problem. ALT Elad Hazan, Sham M. Kakade, Karan Singh
2020	J	`jnl`	What are the Statistical Limits of Offline RL with Linear Function Approximation? CoRR Ruosong Wang, Dean P. Foster, Sham M. Kakade
2019	J	`jnl`	A Short Note on Concentration Inequalities for Random Vectors with SubGaussian Norm. CoRR Chi Jin, Praneeth Netrapalli, Rong Ge, Sham M. Kakade, Michael I. Jordan
2019	J	`jnl`	A Smoother Way to Train Structured Prediction Models. CoRR Venkata Krishna Pillutla, Vincent Roulet, Sham M. Kakade, Zaïd Harchaoui
2019	J	`jnl`	Calibration, Entropy Rates, and Memory in Language Models. CoRR Mark Braverman, Xinyi Chen, Sham M. Kakade, Karthik Narasimhan, Cyril Zhang, Yi Zhang
2019	—	`conf`	Coupled Recurrent Models for Polyphonic Music Composition. ISMIR John Thickstun, Zaïd Harchaoui, Dean P. Foster, Sham M. Kakade
2019	J	`jnl`	Is a Good Representation Sufficient for Sample Efficient Reinforcement Learning? CoRR Simon S. Du, Sham M. Kakade, Ruosong Wang, Lin F. Yang
2019	A*	`conf`	Maximum Likelihood Estimation for Learning Populations of Parameters. ICML Ramya Korlakai Vinayak, Weihao Kong, Gregory Valiant, Sham M. Kakade
2019	J	`jnl`	Maximum Likelihood Estimation for Learning Populations of Parameters. CoRR Ramya Korlakai Vinayak, Weihao Kong, Gregory Valiant, Sham M. Kakade
2019	A*	`conf`	Meta-Learning with Implicit Gradients. NeurIPS Aravind Rajeswaran, Chelsea Finn, Sham M. Kakade, Sergey Levine
2019	J	`jnl`	Meta-Learning with Implicit Gradients. CoRR Aravind Rajeswaran, Chelsea Finn, Sham M. Kakade, Sergey Levine
2019	J	`jnl`	On the Optimality of Sparse Model-Based Planning for Markov Decision Processes. CoRR Alekh Agarwal, Sham M. Kakade, Lin F. Yang
2019	A*	`conf`	Online Control with Adversarial Disturbances. ICML Naman Agarwal, Brian Bullins, Elad Hazan, Sham M. Kakade, Karan Singh
2019	J	`jnl`	Online Control with Adversarial Disturbances. CoRR Naman Agarwal, Brian Bullins, Elad Hazan, Sham M. Kakade, Karan Singh
2019	A*	`conf`	Online Meta-Learning. ICML Chelsea Finn, Aravind Rajeswaran, Sham M. Kakade, Sergey Levine
2019	J	`jnl`	Online Meta-Learning. CoRR Chelsea Finn, Aravind Rajeswaran, Sham M. Kakade, Sergey Levine
2019	A*	`conf`	Open Problem: Do Good Algorithms Necessarily Query Bad Points? COLT Rong Ge, Prateek Jain, Sham M. Kakade, Rahul Kidambi, Dheeraj M. Nagaraj, Praneeth Netrapalli
2019	J	`jnl`	Optimal Estimation of Change in a Population of Parameters. CoRR Ramya Korlakai Vinayak, Weihao Kong, Sham M. Kakade
2019	J	`jnl`	Optimality and Approximation with Policy Gradient Methods in Markov Decision Processes. CoRR Alekh Agarwal, Sham M. Kakade, Jason D. Lee, Gaurav Mahajan
2019	—	`conf`	Plan Online, Learn Offline: Efficient Learning and Exploration via Model-Based Control. ICLR (Poster) Kendall Lowrey, Aravind Rajeswaran, Sham M. Kakade, Emanuel Todorov, Igor Mordatch
2019	A*	`conf`	Provably Efficient Maximum Entropy Exploration. ICML Elad Hazan, Sham M. Kakade, Karan Singh, Abby Van Soest
2019	J	`jnl`	Robust Aggregation for Federated Learning. CoRR Venkata Krishna Pillutla, Sham M. Kakade, Zaïd Harchaoui
2019	J	`jnl`	Stochastic Gradient Descent Escapes Saddle Points Efficiently. CoRR Chi Jin, Praneeth Netrapalli, Rong Ge, Sham M. Kakade, Michael I. Jordan
2019	A*	`conf`	The Illusion of Change: Correcting for Biases in Change Inference for Sparse, Societal-Scale Data. WWW Gabriel Cadamuro, Ramya Korlakai Vinayak, Joshua Blumenstock, Sham M. Kakade, Jacob N. Shapiro
2019	J	`jnl`	The Nonstochastic Control Problem. CoRR Elad Hazan, Sham M. Kakade, Karan Singh
2019	A*	`conf`	The Step Decay Schedule: A Near Optimal, Geometrically Decaying Learning Rate Procedure For Least Squares. NeurIPS Rong Ge, Sham M. Kakade, Rahul Kidambi, Praneeth Netrapalli
2019	J	`jnl`	The Step Decay Schedule: A Near Optimal, Geometrically Decaying Learning Rate Procedure. CoRR Rong Ge, Sham M. Kakade, Rahul Kidambi, Praneeth Netrapalli
2018	A*	`conf`	A Smoother Way to Train Structured Prediction Models. NeurIPS Venkata Krishna Pillutla, Vincent Roulet, Sham M. Kakade, Zaïd Harchaoui
2018	A*	`conf`	Accelerating Stochastic Gradient Descent for Least Squares Regression. COLT Prateek Jain, Sham M. Kakade, Rahul Kidambi, Praneeth Netrapalli, Aaron Sidford
2018	J	`jnl`	Coupled Recurrent Models for Polyphonic Music Composition. CoRR John Thickstun, Zaïd Harchaoui, Dean P. Foster, Sham M. Kakade
2018	J	`jnl`	Global Convergence of Policy Gradient Methods for Linearized Control Problems. CoRR Maryam Fazel, Rong Ge, Sham M. Kakade, Mehran Mesbahi
2018	A*	`conf`	Global Convergence of Policy Gradient Methods for the Linear Quadratic Regulator. ICML Maryam Fazel, Rong Ge, Sham M. Kakade, Mehran Mesbahi
2018	Misc	`conf`	Invariances and Data Augmentation for Supervised Music Transcription. ICASSP John Thickstun, Zaïd Harchaoui, Dean P. Foster, Sham M. Kakade
2018	Misc	`conf`	On the Insufficiency of Existing Momentum Schemes for Stochastic Optimization. ITA Rahul Kidambi, Praneeth Netrapalli, Prateek Jain, Sham M. Kakade
2018	—	`conf`	On the insufficiency of existing momentum schemes for Stochastic Optimization. ICLR Rahul Kidambi, Praneeth Netrapalli, Prateek Jain, Sham M. Kakade
2018	J	`jnl`	On the insufficiency of existing momentum schemes for Stochastic Optimization. CoRR Rahul Kidambi, Praneeth Netrapalli, Prateek Jain, Sham M. Kakade
2018	J	`jnl`	Plan Online, Learn Offline: Efficient Learning and Exploration via Model-Based Control. CoRR Kendall Lowrey, Aravind Rajeswaran, Sham M. Kakade, Emanuel Todorov, Igor Mordatch
2018	A*	`conf`	Prediction with a short memory. STOC Vatsal Sharan, Sham M. Kakade, Percy Liang, Gregory Valiant
2018	A*	`conf`	Provably Correct Automatic Sub-Differentiation for Qualified Programs. NeurIPS Sham M. Kakade, Jason D. Lee
2018	J	`jnl`	Provably Correct Automatic Subdifferentiation for Qualified Programs. CoRR Sham M. Kakade, Jason D. Lee
2018	J	`jnl`	Provably Efficient Maximum Entropy Exploration. CoRR Elad Hazan, Sham M. Kakade, Karan Singh, Abby Van Soest
2018	A	`conf`	Recovering Structured Probability Matrices. ITCS Qingqing Huang, Sham M. Kakade, Weihao Kong, Gregory Valiant
2018	J	`jnl`	Stochastic subgradient method converges on tame functions. CoRR Damek Davis, Dmitriy Drusvyatskiy, Sham M. Kakade, Jason D. Lee
2018	—	`conf`	Variance Reduction for Policy Gradient with Action-Dependent Factorized Baselines. ICLR Cathy Wu, Aravind Rajeswaran, Yan Duan, Vikash Kumar, Alexandre M. Bayen, Sham M. Kakade, Igor Mordatch, Pieter Abbeel
2018	J	`jnl`	Variance Reduction for Policy Gradient with Action-Dependent Factorized Baselines. CoRR Cathy Wu, Aravind Rajeswaran, Yan Duan, Vikash Kumar, Alexandre M. Bayen, Sham M. Kakade, Igor Mordatch, Pieter Abbeel
2017	—	`conf`	A Markov Chain Theory Approach to Characterizing the Minimax Optimality of Stochastic Gradient Descent (for Least Squares). FSTTCS Prateek Jain, Sham M. Kakade, Rahul Kidambi, Praneeth Netrapalli, Venkata Krishna Pillutla, Aaron Sidford
2017	J	`jnl`	A Markov Chain Theory Approach to Characterizing the Minimax Optimality of Stochastic Gradient Descent (for Least Squares). CoRR Prateek Jain, Sham M. Kakade, Rahul Kidambi, Praneeth Netrapalli, Venkata Krishna Pillutla, Aaron Sidford
2017	J	`jnl`	Accelerating Stochastic Gradient Descent. CoRR Prateek Jain, Sham M. Kakade, Rahul Kidambi, Praneeth Netrapalli, Aaron Sidford
2017	A	`conf`	Global Convergence of Non-Convex Gradient Descent for Computing Matrix Squareroot. AISTATS Prateek Jain, Chi Jin, Sham M. Kakade, Praneeth Netrapalli
2017	A*	`conf`	How to Escape Saddle Points Efficiently. ICML Chi Jin, Rong Ge, Praneeth Netrapalli, Sham M. Kakade, Michael I. Jordan
2017	J	`jnl`	How to Escape Saddle Points Efficiently. CoRR Chi Jin, Rong Ge, Praneeth Netrapalli, Sham M. Kakade, Michael I. Jordan
2017	J	`jnl`	Invariances and Data Augmentation for Supervised Music Transcription. CoRR John Thickstun, Zaïd Harchaoui, Dean P. Foster, Sham M. Kakade
2017	—	`conf`	Learning Features of Music From Scratch. ICLR (Poster) John Thickstun, Zaïd Harchaoui, Sham M. Kakade
2017	—	`conf`	Learning Overcomplete HMMs. NIPS Vatsal Sharan, Sham M. Kakade, Percy Liang, Gregory Valiant
2017	J	`jnl`	Learning Overcomplete HMMs. CoRR Vatsal Sharan, Sham M. Kakade, Percy Liang, Gregory Valiant
2017	J	`jnl`	Leverage Score Sampling for Faster Accelerated Regression and ERM. CoRR Naman Agarwal, Sham M. Kakade, Rahul Kidambi, Yin Tat Lee, Praneeth Netrapalli, Aaron Sidford
2017	J	`jnl`	Parallelizing Stochastic Gradient Descent for Least Squares Regression: Mini-batching, Averaging, and Model Misspecification. J. Mach. Learn. Res. Prateek Jain, Sham M. Kakade, Rahul Kidambi, Praneeth Netrapalli, Aaron Sidford
2017	—	`conf`	Towards Generalization and Simplicity in Continuous Control. NIPS Aravind Rajeswaran, Kendall Lowrey, Emanuel Todorov, Sham M. Kakade
2017	J	`jnl`	Towards Generalization and Simplicity in Continuous Control. CoRR Aravind Rajeswaran, Kendall Lowrey, Emanuel Todorov, Sham M. Kakade
2016	J	`jnl`	Canonical Correlation Analysis for Analyzing Sequences of Medical Billing Codes. CoRR Corinne L. Jones, Sham M. Kakade, Lucas W. Thornblade, David R. Flum, Abraham D. Flaxman
2016	A*	`conf`	Efficient Algorithms for Large-scale Generalized Eigenvector Computation and Canonical Correlation Analysis. ICML Rong Ge, Chi Jin, Sham M. Kakade, Praneeth Netrapalli, Aaron Sidford
2016	J	`jnl`	Efficient Algorithms for Large-scale Generalized Eigenvector Computation and Canonical Correlation Analysis. CoRR Rong Ge, Chi Jin, Sham M. Kakade, Praneeth Netrapalli, Aaron Sidford
2016	A*	`conf`	Faster Eigenvector Computation via Shift-and-Invert Preconditioning. ICML Dan Garber, Elad Hazan, Chi Jin, Sham M. Kakade, Cameron Musco, Praneeth Netrapalli, Aaron Sidford
2016	J	`jnl`	Faster Eigenvector Computation via Shift-and-Invert Preconditioning. CoRR Dan Garber, Elad Hazan, Chi Jin, Sham M. Kakade, Cameron Musco, Praneeth Netrapalli, Aaron Sidford
2016	J	`jnl`	Learning Features of Music from Scratch. CoRR John Thickstun, Zaïd Harchaoui, Sham M. Kakade
2016	J	`jnl`	Matching Matrix Bernstein with Little Memory: Near-Optimal Finite Sample Guarantees for Oja's Algorithm. CoRR Prateek Jain, Chi Jin, Sham M. Kakade, Praneeth Netrapalli, Aaron Sidford
2016	J	`jnl`	Minimal Realization Problems for Hidden Markov Models. IEEE Trans. Signal Process. Qingqing Huang, Rong Ge, Sham M. Kakade, Munther A. Dahleh
2016	J	`jnl`	Parallelizing Stochastic Approximation Through Mini-Batching and Tail-Averaging. CoRR Prateek Jain, Sham M. Kakade, Rahul Kidambi, Praneeth Netrapalli, Aaron Sidford
2016	J	`jnl`	Prediction with a Short Memory. CoRR Sham M. Kakade, Percy Liang, Vatsal Sharan, Gregory Valiant
2016	—	`conf`	Provable Efficient Online Matrix Completion via Non-convex Stochastic Gradient Descent. NIPS Chi Jin, Sham M. Kakade, Praneeth Netrapalli
2016	J	`jnl`	Provable Efficient Online Matrix Completion via Non-convex Stochastic Gradient Descent. CoRR Chi Jin, Sham M. Kakade, Praneeth Netrapalli
2016	J	`jnl`	Recovering Structured Probability Matrices. CoRR Qingqing Huang, Sham M. Kakade, Weihao Kong, Gregory Valiant
2016	A*	`conf`	Streaming PCA: Matching Matrix Bernstein and Near-Optimal Finite Sample Guarantees for Oja's Algorithm. COLT Prateek Jain, Chi Jin, Sham M. Kakade, Praneeth Netrapalli, Aaron Sidford
2015	A*	`conf`	A Linear Dynamical System Model for Text. ICML David Belanger, Sham M. Kakade
2015	J	`jnl`	A Linear Dynamical System Model for Text. CoRR David Belanger, Sham M. Kakade
2015	J	`jnl`	A Spectral Algorithm for Latent Dirichlet Allocation. Algorithmica Anima Anandkumar, Dean P. Foster, Daniel J. Hsu, Sham M. Kakade, Yi-Kai Liu
2015	A*	`conf`	Competing with the Empirical Risk Minimizer in a Single Pass. COLT Roy Frostig, Rong Ge, Sham M. Kakade, Aaron Sidford
2015	J	`jnl`	Computing Matrix Squareroot via Non Convex Local Search. CoRR Prateek Jain, Chi Jin, Sham M. Kakade, Praneeth Netrapalli
2015	—	`conf`	Convergence Rates of Active Learning for Maximum Likelihood Estimation. NIPS Kamalika Chaudhuri, Sham M. Kakade, Praneeth Netrapalli, Sujay Sanghavi
2015	J	`jnl`	Convergence Rates of Active Learning for Maximum Likelihood Estimation. CoRR Kamalika Chaudhuri, Sham M. Kakade, Praneeth Netrapalli, Sujay Sanghavi
2015	A*	`conf`	Learning Mixtures of Gaussians in High Dimensions. STOC Rong Ge, Qingqing Huang, Sham M. Kakade
2015	J	`jnl`	Learning Mixtures of Gaussians in High Dimensions. CoRR Rong Ge, Qingqing Huang, Sham M. Kakade
2015	J	`jnl`	Robust Shift-and-Invert Preconditioning: Faster and More Sample Efficient Algorithms for Eigenvector Computation. CoRR Chi Jin, Sham M. Kakade, Cameron Musco, Praneeth Netrapalli, Aaron Sidford
2015	—	`conf`	Super-Resolution Off the Grid. NIPS Qingqing Huang, Sham M. Kakade
2015	J	`jnl`	Super-Resolution Off the Grid. CoRR Qingqing Huang, Sham M. Kakade
2015	B	`conf`	Tensor Decompositions for Learning Latent Variable Models (A Survey for ALT). ALT Anima Anandkumar, Rong Ge, Daniel J. Hsu, Sham M. Kakade, Matus Telgarsky
2015	A*	`conf`	Un-regularizing: approximate proximal point and faster stochastic algorithms for empirical risk minimization. ICML Roy Frostig, Rong Ge, Sham M. Kakade, Aaron Sidford
2015	J	`jnl`	Un-regularizing: approximate proximal point and faster stochastic algorithms for empirical risk minimization. CoRR Roy Frostig, Rong Ge, Sham M. Kakade, Aaron Sidford
2015	J	`jnl`	When are overcomplete topic models identifiable? uniqueness of tensor tucker decompositions with structured sparsity. J. Mach. Learn. Res. Animashree Anandkumar, Daniel J. Hsu, Majid Janzamin, Sham M. Kakade
2014	J	`jnl`	A tensor approach to learning mixed membership community models. J. Mach. Learn. Res. Animashree Anandkumar, Rong Ge, Daniel J. Hsu, Sham M. Kakade
2014	J	`jnl`	Competing with the Empirical Risk Minimizer in a Single Pass. CoRR Roy Frostig, Rong Ge, Sham M. Kakade, Aaron Sidford
2014	A*	`conf`	Least Squares Revisited: Scalable Approaches for Multi-class Prediction. ICML Alekh Agarwal, Sham M. Kakade, Nikos Karampatziakis, Le Song, Gregory Valiant
2014	J	`jnl`	Minimal Realization Problems for Hidden Markov Models. CoRR Qingqing Huang, Rong Ge, Sham M. Kakade, Munther A. Dahleh
2014	—	`conf`	Minimal realization problem for Hidden Markov Models. Allerton Qingqing Huang, Rong Ge, Sham M. Kakade, Munther A. Dahleh
2014	J	`jnl`	Random Design Analysis of Ridge Regression. Found. Comput. Math. Daniel J. Hsu, Sham M. Kakade, Tong Zhang
2014	J	`jnl`	Tensor decompositions for learning latent variable models. J. Mach. Learn. Res. Animashree Anandkumar, Rong Ge, Daniel J. Hsu, Sham M. Kakade, Matus Telgarsky
2013	J	`jnl`	A Tensor Spectral Approach to Learning Mixed Membership Community Models CoRR Anima Anandkumar, Rong Ge, Daniel J. Hsu, Sham M. Kakade
2013	A*	`conf`	A Tensor Spectral Approach to Learning Mixed Membership Community Models. COLT Animashree Anandkumar, Rong Ge, Daniel J. Hsu, Sham M. Kakade
2013	J	`jnl`	A risk comparison of ordinary least squares vs ridge regression. J. Mach. Learn. Res. Paramveer S. Dhillon, Dean P. Foster, Sham M. Kakade, Lyle H. Ungar
2013	—	`conf`	Learning Linear Bayesian Networks with Latent Variables. ICML (1) Animashree Anandkumar, Daniel J. Hsu, Adel Javanmard, Sham M. Kakade
2013	A	`conf`	Learning mixtures of spherical gaussians: moment methods and spectral decompositions. ITCS Daniel J. Hsu, Sham M. Kakade
2013	J	`jnl`	Least Squares Revisited: Scalable Approaches for Multi-class Prediction. CoRR Alekh Agarwal, Sham M. Kakade, Nikos Karampatziakis, Le Song, Gregory Valiant
2013	J	`jnl`	Optimal Dynamic Mechanism Design and the Virtual-Pivot Mechanism. Oper. Res. Sham M. Kakade, Ilan Lobel, Hamid Nazerzadeh
2013	J	`jnl`	Stochastic Convex Optimization with Bandit Feedback. SIAM J. Optim. Alekh Agarwal, Dean P. Foster, Daniel J. Hsu, Sham M. Kakade, Alexander Rakhlin
2013	—	`conf`	When are Overcomplete Topic Models Identifiable? Uniqueness of Tensor Tucker Decompositions with Structured Sparsity. NIPS Anima Anandkumar, Daniel J. Hsu, Majid Janzamin, Sham M. Kakade
2013	J	`jnl`	When are Overcomplete Topic Models Identifiable? Uniqueness of Tensor Tucker Decompositions with Structured Sparsity. CoRR Animashree Anandkumar, Daniel J. Hsu, Majid Janzamin, Sham M. Kakade
2012	J	`jnl`	(weak) Calibration is Computationally Hard CoRR Elad Hazan, Sham M. Kakade
2012	A*	`conf`	(weak) Calibration is Computationally Hard. COLT Elad Hazan, Sham M. Kakade
2012	J	`jnl`	A Method of Moments for Mixture Models and Hidden Markov Models CoRR Animashree Anandkumar, Daniel J. Hsu, Sham M. Kakade
2012	A*	`conf`	A Method of Moments for Mixture Models and Hidden Markov Models. COLT Animashree Anandkumar, Daniel J. Hsu, Sham M. Kakade
2012	—	`conf`	A Spectral Algorithm for Latent Dirichlet Allocation. NIPS Anima Anandkumar, Dean P. Foster, Daniel J. Hsu, Sham M. Kakade, Yi-Kai Liu
2012	J	`jnl`	A spectral algorithm for learning Hidden Markov Models. J. Comput. Syst. Sci. Daniel J. Hsu, Sham M. Kakade, Tong Zhang
2012	J	`jnl`	Analysis of a randomized approximation scheme for matrix multiplication CoRR Daniel J. Hsu, Sham M. Kakade, Tong Zhang
2012	A	`conf`	Domain Adaptation: A Small Sample Statistical Approach. AISTATS Ruslan Salakhutdinov, Sham M. Kakade, Dean P. Foster
2012	J	`jnl`	Identifiability and Unmixing of Latent Parse Trees CoRR Daniel J. Hsu, Sham M. Kakade, Percy Liang
2012	—	`conf`	Identifiability and Unmixing of Latent Parse Trees. NIPS Daniel J. Hsu, Sham M. Kakade, Percy Liang
2012	J	`jnl`	Information-Theoretic Regret Bounds for Gaussian Process Optimization in the Bandit Setting. IEEE Trans. Inf. Theory Niranjan Srinivas, Andreas Krause, Sham M. Kakade, Matthias W. Seeger
2012	J	`jnl`	Learning Gaussian Mixture Models: Moment Methods and Spectral Decompositions CoRR Daniel J. Hsu, Sham M. Kakade
2012	J	`jnl`	Learning High-Dimensional Mixtures of Graphical Models CoRR Animashree Anandkumar, Daniel J. Hsu, Sham M. Kakade
2012	J	`jnl`	Learning Linear Bayesian Networks with Latent Variables CoRR Animashree Anandkumar, Daniel J. Hsu, Adel Javanmard, Sham M. Kakade
2012	—	`conf`	Learning Mixtures of Tree Graphical Models. NIPS Animashree Anandkumar, Daniel J. Hsu, Furong Huang, Sham M. Kakade
2012	J	`jnl`	Planning in POMDPs Using Multiplicity Automata CoRR Eyal Even-Dar, Sham M. Kakade, Yishay Mansour
2012	A*	`conf`	Random Design Analysis of Ridge Regression. COLT Daniel J. Hsu, Sham M. Kakade, Tong Zhang
2012	J	`jnl`	Regularization Techniques for Learning with Matrices. J. Mach. Learn. Res. Sham M. Kakade, Shai Shalev-Shwartz, Ambuj Tewari
2012	J	`jnl`	Tensor decompositions for learning latent variable models CoRR Anima Anandkumar, Rong Ge, Daniel J. Hsu, Sham M. Kakade, Matus Telgarsky
2012	A*	`conf`	Towards Minimax Policies for Online Linear Optimization with Bandit Feedback. COLT Sébastien Bubeck, Nicolò Cesa-Bianchi, Sham M. Kakade
2012	J	`jnl`	Towards minimax policies for online linear optimization with bandit feedback CoRR Sébastien Bubeck, Nicolò Cesa-Bianchi, Sham M. Kakade
2012	J	`jnl`	Two SVDs Suffice: Spectral decompositions for probabilistic topic modeling and latent Dirichlet allocation CoRR Animashree Anandkumar, Dean P. Foster, Daniel J. Hsu, Sham M. Kakade, Yi-Kai Liu
2011	J	`jnl`	A tail inequality for quadratic forms of subgaussian random vectors CoRR Daniel J. Hsu, Sham M. Kakade, Tong Zhang
2011	J	`jnl`	An Analysis of Random Design Linear Regression CoRR Daniel J. Hsu, Sham M. Kakade, Tong Zhang
2011	A*	`ed.`	COLT 2011 - The 24th Annual Conference on Learning Theory, June 9-11, 2011, Budapest, Hungary COLT Sham M. Kakade, Ulrike von Luxburg
2011	J	`jnl`	Dimension-free tail inequalities for sums of random matrices. CoRR Daniel J. Hsu, Sham M. Kakade, Tong Zhang
2011	A	`conf`	Domain Adaptation with Coupled Subspaces. AISTATS John Blitzer, Sham M. Kakade, Dean P. Foster
2011	J	`jnl`	Domain Adaptation: Overfitting and Small Sample Statistics CoRR Dean P. Foster, Sham M. Kakade, Ruslan Salakhutdinov
2011	J	`jnl`	Efficient Learning of Generalized Linear and Single Index Models with Isotonic Regression CoRR Sham M. Kakade, Adam Tauman Kalai, Varun Kanade, Ohad Shamir
2011	—	`conf`	Efficient Learning of Generalized Linear and Single Index Models with Isotonic Regression. NIPS Sham M. Kakade, Adam Kalai, Varun Kanade, Ohad Shamir
2011	J	`jnl`	Optimal dynamic mechanism design via a virtual VCG mechanism. SIGecom Exch. Sham M. Kakade, Ilan Lobel, Hamid Nazerzadeh
2011	A*	`conf`	Preface. COLT Sham M. Kakade, Ulrike von Luxburg
2011	J	`jnl`	Robust Matrix Decomposition With Sparse Corruptions. IEEE Trans. Inf. Theory Daniel J. Hsu, Sham M. Kakade, Tong Zhang
2011	J	`jnl`	Spectral Methods for Learning Multivariate Latent Tree Structure CoRR Animashree Anandkumar, Kamalika Chaudhuri, Daniel J. Hsu, Sham M. Kakade, Le Song, Tong Zhang
2011	—	`conf`	Spectral Methods for Learning Multivariate Latent Tree Structure. NIPS Animashree Anandkumar, Kamalika Chaudhuri, Daniel J. Hsu, Sham M. Kakade, Le Song, Tong Zhang
2011	J	`jnl`	Stochastic convex optimization with bandit feedback CoRR Alekh Agarwal, Dean P. Foster, Daniel J. Hsu, Sham M. Kakade, Alexander Rakhlin
2011	—	`conf`	Stochastic convex optimization with bandit feedback. NIPS Alekh Agarwal, Dean P. Foster, Daniel J. Hsu, Sham M. Kakade, Alexander Rakhlin
2010	J	`jnl`	An Optimal Dynamic Mechanism for Multi-Armed Bandit Processes CoRR Sham M. Kakade, Ilan Lobel, Hamid Nazerzadeh
2010	A*	`conf`	Gaussian Process Optimization in the Bandit Setting: No Regret and Experimental Design. ICML Niranjan Srinivas, Andreas Krause, Sham M. Kakade, Matthias W. Seeger
2010	J	`jnl`	Guest editorial: special issue on learning theory. Mach. Learn. Sham M. Kakade, Ping Li
2010	A	`conf`	Learning Exponential Families in High-Dimensions: Strong Convexity and Sparsity. AISTATS Sham M. Kakade, Ohad Shamir, Karthik Sindharan, Ambuj Tewari
2010	J	`jnl`	Learning from Logged Implicit Exploration Data CoRR Alexander L. Strehl, John Langford, Sham M. Kakade
2010	—	`conf`	Learning from Logged Implicit Exploration Data. NIPS Alexander L. Strehl, John Langford, Lihong Li, Sham M. Kakade
2010	J	`jnl`	Robust Matrix Decomposition with Outliers CoRR Daniel J. Hsu, Sham M. Kakade, Tong Zhang
2009	A*	`conf`	A Spectral Algorithm for Learning Hidden Markov Models. COLT Daniel J. Hsu, Sham M. Kakade, Tong Zhang
2009	J	`jnl`	Applications of strong convexity--strong smoothness duality to learning with matrices CoRR Sham M. Kakade, Shai Shalev-Shwartz, Ambuj Tewari
2009	J	`jnl`	Gaussian Process Bandits without Regret: An Experimental Design Approach CoRR Niranjan Srinivas, Andreas Krause, Sham M. Kakade, Matthias W. Seeger
2009	J	`jnl`	Learning Exponential Families in High-Dimensions: Strong Convexity and Sparsity CoRR Sham M. Kakade, Ohad Shamir, Karthik Sridharan, Ambuj Tewari
2009	J	`jnl`	Multi-Label Prediction via Compressed Sensing CoRR Daniel J. Hsu, Sham M. Kakade, John Langford, Tong Zhang
2009	—	`conf`	Multi-Label Prediction via Compressed Sensing. NIPS Daniel J. Hsu, Sham M. Kakade, John Langford, Tong Zhang
2009	A*	`conf`	Multi-view clustering via canonical correlation analysis. ICML Kamalika Chaudhuri, Sham M. Kakade, Karen Livescu, Karthik Sridharan
2009	J	`jnl`	Online Markov Decision Processes. Math. Oper. Res. Eyal Even-Dar, Sham M. Kakade, Yishay Mansour
2009	J	`jnl`	Playing Games with Approximation Algorithms. SIAM J. Comput. Sham M. Kakade, Adam Tauman Kalai, Katrina Ligett
2009	A*	`conf`	The price of truthfulness for pay-per-click auctions. EC Nikhil R. Devanur, Sham M. Kakade
2008	J	`jnl`	A Spectral Algorithm for Learning Hidden Markov Models CoRR Daniel J. Hsu, Sham M. Kakade, Tong Zhang
2008	A*	`conf`	An Information Theoretic Framework for Multi-view Learning. COLT Karthik Sridharan, Sham M. Kakade
2008	J	`jnl`	Deterministic calibration and Nash equilibrium. J. Comput. Syst. Sci. Sham M. Kakade, Dean P. Foster
2008	A*	`conf`	Efficient bandit algorithms for online multiclass prediction. ICML Sham M. Kakade, Shai Shalev-Shwartz, Ambuj Tewari
2008	A*	`conf`	High-Probability Regret Bounds for Bandit Online Linear Optimization. COLT Peter L. Bartlett, Varsha Dani, Thomas P. Hayes, Sham M. Kakade, Alexander Rakhlin, Ambuj Tewari
2008	J	`jnl`	Information Consistency of Nonparametric Gaussian Process Methods. IEEE Trans. Inf. Theory Matthias W. Seeger, Sham M. Kakade, Dean P. Foster
2008	—	`conf`	Mind the Duality Gap: Logarithmic regret algorithms for online optimization. NIPS Shai Shalev-Shwartz, Sham M. Kakade
2008	—	`conf`	On the Complexity of Linear Prediction: Risk Bounds, Margin Bounds, and Regularization. NIPS Sham M. Kakade, Karthik Sridharan, Ambuj Tewari
2008	—	`conf`	On the Generalization Ability of Online Strongly Convex Programming Algorithms. NIPS Sham M. Kakade, Ambuj Tewari
2008	A*	`conf`	Stochastic Linear Optimization under Bandit Feedback. COLT Varsha Dani, Thomas P. Hayes, Sham M. Kakade
2007	A*	`conf`	Leveragingarchivalvideo for building face datasets. ICCV Deva Ramanan, Simon Baker, Sham M. Kakade
2007	A	`conf`	Maximum Entropy Correlated Equilibria. AISTATS Luis E. Ortiz, Robert E. Schapire, Sham M. Kakade
2007	A*	`conf`	Multi-view Regression Via Canonical Correlation Analysis. COLT Sham M. Kakade, Dean P. Foster
2007	A*	`conf`	Playing games with approximation algorithms. STOC Sham M. Kakade, Adam Tauman Kalai, Katrina Ligett
2007	—	`conf`	The Price of Bandit Information for Online Optimization. NIPS Varsha Dani, Thomas P. Hayes, Sham M. Kakade
2007	A*	`conf`	The Value of Observation for Monitoring Dynamic Systems. IJCAI Eyal Even-Dar, Sham M. Kakade, Yishay Mansour
2006	A*	`conf`	(In)Stability properties of limit order dynamics. EC Eyal Even-Dar, Sham M. Kakade, Michael J. Kearns, Yishay Mansour
2006	B	`conf`	Calibration via Regression. ITW Dean P. Foster, Sham M. Kakade
2006	A*	`conf`	Cover trees for nearest neighbor. ICML Alina Beygelzimer, Sham M. Kakade, John Langford
2005	—	`conf`	From Batch to Transductive Online Learning. NIPS Sham M. Kakade, Adam Kalai
2005	A	`conf`	Planning in POMDPs Using Multiplicity Automata. UAI Eyal Even-Dar, Sham M. Kakade, Yishay Mansour
2005	A*	`conf`	Reinforcement Learning in POMDPs Without Resets. IJCAI Eyal Even-Dar, Sham M. Kakade, Yishay Mansour
2005	A*	`conf`	Trading in Markovian Price Models. COLT Sham M. Kakade, Michael J. Kearns
2005	—	`conf`	Worst-Case Bounds for Gaussian Process Models. NIPS Sham M. Kakade, Matthias W. Seeger, Dean P. Foster
2004	A*	`conf`	Competitive algorithms for VWAP and limit order trading. EC Sham M. Kakade, Michael J. Kearns, Yishay Mansour, Luis E. Ortiz
2004	A*	`conf`	Deterministic Calibration and Nash Equilibrium. COLT Sham M. Kakade, Dean P. Foster
2004	—	`conf`	Economic Properties of Social Networks. NIPS Sham M. Kakade, Michael J. Kearns, Luis E. Ortiz, Robin Pemantle, Siddharth Suri
2004	—	`conf`	Experts in a Markov Decision Process. NIPS Eyal Even-Dar, Sham M. Kakade, Yishay Mansour
2004	A*	`conf`	Graphical Economics. COLT Sham M. Kakade, Michael J. Kearns, Luis E. Ortiz
2004	—	`conf`	Online Bounds for Bayesian Algorithms. NIPS Sham M. Kakade, Andrew Y. Ng
2003	A*	`conf`	Correlated equilibria in graphical games. EC Sham M. Kakade, Michael J. Kearns, John Langford, Luis E. Ortiz
2003	A*	`conf`	Exploration in Metric State Spaces. ICML Sham M. Kakade, Michael J. Kearns, John Langford
2003	—	`conf`	Policy Search by Dynamic Programming. NIPS J. Andrew Bagnell, Sham M. Kakade, Andrew Y. Ng, Jeff G. Schneider
2002	A*	`conf`	An Alternate Objective Function for Markovian Fields. ICML Sham M. Kakade, Yee Whye Teh, Sam T. Roweis
2002	A*	`conf`	Approximately Optimal Approximate Reinforcement Learning. ICML Sham M. Kakade, John Langford
2002	A*	`conf`	Competitive Analysis of the Explore/Exploit Tradeoff. ICML John Langford, Martin Zinkevich, Sham M. Kakade
2002	J	`jnl`	Dopamine: generalization and bonuses. Neural Networks Sham M. Kakade, Peter Dayan
2002	J	`jnl`	Opponent interactions between serotonin and dopamine. Neural Networks Nathaniel D. Daw, Sham M. Kakade, Peter Dayan
2001	—	`conf`	A Natural Policy Gradient. NIPS Sham M. Kakade
2001	—	`conf`	Optimizing Average Reward Using Discounted Rewards. COLT/EuroCOLT Sham M. Kakade
2000	—	`conf`	Dopamine Bonuses. NIPS Sham M. Kakade, Peter Dayan
2000	—	`conf`	Explaining Away in Weight Space. NIPS Peter Dayan, Sham M. Kakade
1999	—	`conf`	Acquisition in Autoshaping. NIPS Sham M. Kakade, Peter Dayan