Akshay Krishnamurthy

193 papers A* 67A 6B 4Misc 2Journal 104Unranked 10

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	A Unifying View of Coverage in Linear Off-Policy Evaluation. CoRR Philip Amortila, Audrey Huang, Akshay Krishnamurthy, Nan Jiang
2026	J	`jnl`	Learning to Reason with Curriculum I: Provable Benefits of Autocurriculum. CoRR Nived Rajaraman, Audrey Huang, Miroslav Dudík, Robert E. Schapire, Dylan J. Foster, Akshay Krishnamurthy
2026	J	`jnl`	Reject, Resample, Repeat: Understanding Parallel Reasoning in Language Model Inference. CoRR Noah Golowich, Fan Chen, Dhruv Rohatgi, Raghav Singhal, Carles Domingo-Enrich, Dylan J. Foster, Akshay Krishnamurthy
2025	A*	`conf`	Computational-Statistical Tradeoffs at the Next-Token Prediction Barrier: Autoregressive and Imitation Learning under Misspecification (extended abstract). COLT Dhruv Rohatgi, Adam Block, Audrey Huang, Akshay Krishnamurthy, Dylan J. Foster
2025	J	`jnl`	Computational-Statistical Tradeoffs at the Next-Token Prediction Barrier: Autoregressive and Imitation Learning under Misspecification. CoRR Dhruv Rohatgi, Adam Block, Audrey Huang, Akshay Krishnamurthy, Dylan J. Foster
2025	A*	`conf`	Computationally Efficient RL under Linear Bellman Completeness for Deterministic Dynamics. ICLR Runzhe Wu, Ayush Sekhari, Akshay Krishnamurthy, Wen Sun
2025	A*	`conf`	Correcting the Mythos of KL-Regularization: Direct Alignment without Overoptimization via Chi-Squared Preference Optimization. ICLR Audrey Huang, Wenhao Zhan, Tengyang Xie, Jason D. Lee, Wen Sun, Akshay Krishnamurthy, Dylan J. Foster
2025	A*	`conf`	Exploratory Preference Optimization: Harnessing Implicit Q*-Approximation for Sample-Efficient RLHF. ICLR Tengyang Xie, Dylan J. Foster, Akshay Krishnamurthy, Corby Rosset, Ahmed Hassan Awadallah, Alexander Rakhlin
2025	A*	`conf`	Is Best-of-N the Best of Them? Coverage, Scaling, and Optimality in Inference-Time Alignment. ICML Audrey Huang, Adam Block, Qinghua Liu, Nan Jiang, Akshay Krishnamurthy, Dylan J. Foster
2025	J	`jnl`	Is Best-of-N the Best of Them? Coverage, Scaling, and Optimality in Inference-Time Alignment. CoRR Audrey Huang, Adam Block, Qinghua Liu, Nan Jiang, Dylan J. Foster, Akshay Krishnamurthy
2025	J	`jnl`	Representation-Based Exploration for Language Models: From Test-Time to Post-Training. CoRR Jens Tuyls, Dylan J. Foster, Akshay Krishnamurthy, Jordan T. Ash
2025	A*	`conf`	Self-Improvement in Language Models: The Sharpening Mechanism. ICLR Audrey Huang, Adam Block, Dylan J. Foster, Dhruv Rohatgi, Cyril Zhang, Max Simchowitz, Jordan T. Ash, Akshay Krishnamurthy
2025	J	`jnl`	The Coverage Principle: How Pre-Training Enables Post-Training. CoRR Fan Chen, Audrey Huang, Noah Golowich, Sadhika Malladi, Adam Block, Jordan T. Ash, Akshay Krishnamurthy, Dylan J. Foster
2025	A*	`conf`	The Role of Environment Access in Agnostic Reinforcement Learning (Extended Abstract). COLT Akshay Krishnamurthy, Gene Li, Ayush Sekhari
2025	J	`jnl`	The Role of Environment Access in Agnostic Reinforcement Learning. CoRR Akshay Krishnamurthy, Gene Li, Ayush Sekhari
2025	J	`jnl`	Wait, Wait, Wait... Why Do Reasoning Models Loop? CoRR Charilaos Pipis, Shivam Garg, Vasilis Kontonis, Vaishnavi Shrivastava, Akshay Krishnamurthy, Dimitris Papailiopoulos
2024	A*	`conf`	Butterfly Effects of SGD Noise: Error Amplification in Behavior Cloning and Autoregression. ICLR Adam Block, Dylan J. Foster, Akshay Krishnamurthy, Max Simchowitz, Cyril Zhang
2024	A*	`conf`	Can large language models explore in-context? NeurIPS Akshay Krishnamurthy, Keegan Harris, Dylan J. Foster, Cyril Zhang, Aleksandrs Slivkins
2024	J	`jnl`	Can large language models explore in-context? CoRR Akshay Krishnamurthy, Keegan Harris, Dylan J. Foster, Cyril Zhang, Aleksandrs Slivkins
2024	J	`jnl`	Computationally Efficient RL under Linear Bellman Completeness for Deterministic Dynamics. CoRR Runzhe Wu, Ayush Sekhari, Akshay Krishnamurthy, Wen Sun
2024	J	`jnl`	Correcting the Mythos of KL-Regularization: Direct Alignment without Overoptimization via Chi-Squared Preference Optimization. CoRR Audrey Huang, Wenhao Zhan, Tengyang Xie, Jason D. Lee, Wen Sun, Akshay Krishnamurthy, Dylan J. Foster
2024	J	`jnl`	Exploratory Preference Optimization: Harnessing Implicit Q*-Approximation for Sample-Efficient RLHF. CoRR Tengyang Xie, Dylan J. Foster, Akshay Krishnamurthy, Corby Rosset, Ahmed Awadallah, Alexander Rakhlin
2024	A*	`conf`	Mitigating Covariate Shift in Misspecified Regression with Applications to Reinforcement Learning. COLT Philip Amortila, Tongyi Cao, Akshay Krishnamurthy
2024	J	`jnl`	Mitigating Covariate Shift in Misspecified Regression with Applications to Reinforcement Learning. CoRR Philip Amortila, Tongyi Cao, Akshay Krishnamurthy
2024	J	`jnl`	Model-Free Representation Learning and Exploration in Low-Rank MDPs. J. Mach. Learn. Res. Aditya Modi, Jinglin Chen, Akshay Krishnamurthy, Nan Jiang, Alekh Agarwal
2024	A	`conf`	Oracle-Efficient Pessimism: Offline Policy Optimization In Contextual Bandits. AISTATS Lequn Wang, Akshay Krishnamurthy, Alex Slivkins
2024	A*	`conf`	Reinforcement Learning Under Latent Dynamics: Toward Statistical and Algorithmic Modularity. NeurIPS Philip Amortila, Dylan J. Foster, Nan Jiang, Akshay Krishnamurthy, Zakaria Mhammedi
2024	J	`jnl`	Reinforcement Learning under Latent Dynamics: Toward Statistical and Algorithmic Modularity. CoRR Philip Amortila, Dylan J. Foster, Nan Jiang, Akshay Krishnamurthy, Zakaria Mhammedi
2024	A*	`conf`	Rich-Observation Reinforcement Learning with Continuous Latent Dynamics. ICML Yuda Song, Lili Wu, Dylan J. Foster, Akshay Krishnamurthy
2024	J	`jnl`	Rich-Observation Reinforcement Learning with Continuous Latent Dynamics. CoRR Yuda Song, Lili Wu, Dylan J. Foster, Akshay Krishnamurthy
2024	J	`jnl`	Robust Dynamic Assortment Optimization in the Presence of Outlier Customers. Oper. Res. Xi Chen, Akshay Krishnamurthy, Yining Wang
2024	A*	`conf`	Scalable Online Exploration via Coverability. ICML Philip Amortila, Dylan J. Foster, Akshay Krishnamurthy
2024	J	`jnl`	Scalable Online Exploration via Coverability. CoRR Philip Amortila, Dylan J. Foster, Akshay Krishnamurthy
2024	J	`jnl`	Self-Improvement in Language Models: The Sharpening Mechanism. CoRR Audrey Huang, Adam Block, Dylan J. Foster, Dhruv Rohatgi, Cyril Zhang, Max Simchowitz, Jordan T. Ash, Akshay Krishnamurthy
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`	Butterfly Effects of SGD Noise: Error Amplification in Behavior Cloning and Autoregression. CoRR Adam Block, Dylan J. Foster, Akshay Krishnamurthy, Max Simchowitz, Cyril Zhang
2023	J	`jnl`	Contextual Search in the Presence of Adversarial Corruptions. Oper. Res. Akshay Krishnamurthy, Thodoris Lykouris, Chara Podimata, Robert E. Schapire
2023	A*	`conf`	Exposing Attention Glitches with Flip-Flop Language Modeling. NeurIPS Bingbin Liu, Jordan T. Ash, Surbhi Goel, Akshay Krishnamurthy, Cyril Zhang
2023	J	`jnl`	Exposing Attention Glitches with Flip-Flop Language Modeling. CoRR Bingbin Liu, Jordan T. Ash, Surbhi Goel, Akshay Krishnamurthy, Cyril Zhang
2023	J	`jnl`	Guaranteed Discovery of Control-Endogenous Latent States with Multi-Step Inverse Models. Trans. Mach. Learn. Res. Alex Lamb, Riashat Islam, Yonathan Efroni, Aniket Rajiv Didolkar, Dipendra Misra, Dylan J. Foster, Lekan P. Molu, Rajan Chari, Akshay Krishnamurthy, John Langford
2023	A*	`conf`	Hybrid RL: Using both offline and online data can make RL efficient. ICLR Yuda Song, Yifei Zhou, Ayush Sekhari, Drew Bagnell, Akshay Krishnamurthy, Wen Sun
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`	Oracle-Efficient Pessimism: Offline Policy Optimization in Contextual Bandits. CoRR Lequn Wang, Akshay Krishnamurthy, Aleksandrs Slivkins
2023	A*	`conf`	Statistical Learning under Heterogenous Distribution Shift. ICML Max Simchowitz, Anurag Ajay, Pulkit Agrawal, Akshay Krishnamurthy
2023	J	`jnl`	Statistical Learning under Heterogenous Distribution Shift. CoRR Max Simchowitz, Anurag Ajay, Pulkit Agrawal, Akshay Krishnamurthy
2023	A*	`conf`	Streaming Active Learning with Deep Neural Networks. ICML Akanksha Saran, Safoora Yousefi, Akshay Krishnamurthy, John Langford, Jordan T. Ash
2023	J	`jnl`	Streaming Active Learning with Deep Neural Networks. CoRR Akanksha Saran, Safoora Yousefi, Akshay Krishnamurthy, John Langford, Jordan T. Ash
2023	A*	`conf`	Transformers Learn Shortcuts to Automata. ICLR Bingbin Liu, Jordan T. Ash, Surbhi Goel, Akshay Krishnamurthy, Cyril Zhang
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	B	`conf`	Efficient and Optimal Algorithms for Contextual Dueling Bandits under Realizability. ALT Aadirupa Saha, Akshay Krishnamurthy
2022	J	`jnl`	Guaranteed Discovery of Controllable Latent States with Multi-Step Inverse Models. CoRR Alex Lamb, Riashat Islam, Yonathan Efroni, Aniket Didolkar, Dipendra Misra, Dylan J. Foster, Lekan P. Molu, Rajan Chari, Akshay Krishnamurthy, John Langford
2022	J	`jnl`	Hybrid RL: Using Both Offline and Online Data Can Make RL Efficient. CoRR Yuda Song, Yifei Zhou, Ayush Sekhari, J. Andrew Bagnell, Akshay Krishnamurthy, Wen Sun
2022	A	`conf`	Investigating the Role of Negatives in Contrastive Representation Learning. AISTATS Jordan T. Ash, Surbhi Goel, Akshay Krishnamurthy, Dipendra Misra
2022	A*	`conf`	Offline Reinforcement Learning: Fundamental Barriers for Value Function Approximation. COLT Dylan J. Foster, Akshay Krishnamurthy, David Simchi-Levi, Yunzong Xu
2022	A*	`conf`	On the Statistical Efficiency of Reward-Free Exploration in Non-Linear RL. NeurIPS Jinglin Chen, Aditya Modi, Akshay Krishnamurthy, Nan Jiang, Alekh Agarwal
2022	J	`jnl`	On the Statistical Efficiency of Reward-Free Exploration in Non-Linear RL. CoRR Jinglin Chen, Aditya Modi, Akshay Krishnamurthy, Nan Jiang, Alekh Agarwal
2022	A*	`conf`	Provable Reinforcement Learning with a Short-Term Memory. ICML Yonathan Efroni, Chi Jin, Akshay Krishnamurthy, Sobhan Miryoosefi
2022	J	`jnl`	Provable Reinforcement Learning with a Short-Term Memory. CoRR Yonathan Efroni, Chi Jin, Akshay Krishnamurthy, Sobhan Miryoosefi
2022	A*	`conf`	Provably Filtering Exogenous Distractors using Multistep Inverse Dynamics. ICLR Yonathan Efroni, Dipendra Misra, Akshay Krishnamurthy, Alekh Agarwal, John Langford
2022	A*	`conf`	Sample-Efficient Reinforcement Learning in the Presence of Exogenous Information. COLT Yonathan Efroni, Dylan J. Foster, Dipendra Misra, Akshay Krishnamurthy, John Langford
2022	J	`jnl`	Sample-Efficient Reinforcement Learning in the Presence of Exogenous Information. CoRR Yonathan Efroni, Dylan J. Foster, Dipendra Misra, Akshay Krishnamurthy, John Langford
2022	A*	`conf`	Sparsity in Partially Controllable Linear Systems. ICML Yonathan Efroni, Sham M. Kakade, Akshay Krishnamurthy, Cyril Zhang
2022	J	`jnl`	Transformers Learn Shortcuts to Automata. CoRR Bingbin Liu, Jordan T. Ash, Surbhi Goel, Akshay Krishnamurthy, Cyril Zhang
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`	Universal and data-adaptive algorithms for model selection in linear contextual bandits. ICML Vidya K. Muthukumar, Akshay Krishnamurthy
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`	Bayesian decision-making under misspecified priors with applications to meta-learning. NeurIPS Max Simchowitz, Christopher Tosh, Akshay Krishnamurthy, Daniel J. Hsu, Thodoris Lykouris, Miroslav Dudík, Robert E. Schapire
2021	J	`jnl`	Bayesian decision-making under misspecified priors with applications to meta-learning. CoRR Max Simchowitz, Christopher Tosh, Akshay Krishnamurthy, Daniel Hsu, Thodoris Lykouris, Miroslav Dudík, Robert E. Schapire
2021	A*	`conf`	Contextual search in the presence of irrational agents. STOC Akshay Krishnamurthy, Thodoris Lykouris, Chara Podimata, Robert E. Schapire
2021	J	`jnl`	Contrastive Estimation Reveals Topic Posterior Information to Linear Models. J. Mach. Learn. Res. Christopher Tosh, Akshay Krishnamurthy, Daniel Hsu
2021	B	`conf`	Contrastive learning, multi-view redundancy, and linear models. ALT Christopher Tosh, Akshay Krishnamurthy, Daniel Hsu
2021	A*	`conf`	Efficient First-Order Contextual Bandits: Prediction, Allocation, and Triangular Discrimination. NeurIPS Dylan J. Foster, Akshay Krishnamurthy
2021	J	`jnl`	Efficient First-Order Contextual Bandits: Prediction, Allocation, and Triangular Discrimination. CoRR Dylan J. Foster, Akshay Krishnamurthy
2021	J	`jnl`	Efficient and Optimal Algorithms for Contextual Dueling Bandits under Realizability. CoRR Aadirupa Saha, Akshay Krishnamurthy
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	J	`jnl`	Investigating the Role of Negatives in Contrastive Representation Learning. CoRR Jordan T. Ash, Surbhi Goel, Akshay Krishnamurthy, Dipendra Misra
2021	J	`jnl`	Model-free Representation Learning and Exploration in Low-rank MDPs. CoRR Aditya Modi, Jinglin Chen, Akshay Krishnamurthy, Nan Jiang, Alekh Agarwal
2021	J	`jnl`	Offline Reinforcement Learning: Fundamental Barriers for Value Function Approximation. CoRR Dylan J. Foster, Akshay Krishnamurthy, David Simchi-Levi, Yunzong Xu
2021	A*	`conf`	Optimism in Reinforcement Learning with Generalized Linear Function Approximation. ICLR Yining Wang, Ruosong Wang, Simon Shaolei Du, Akshay Krishnamurthy
2021	J	`jnl`	Provable RL with Exogenous Distractors via Multistep Inverse Dynamics. CoRR Yonathan Efroni, Dipendra Misra, Akshay Krishnamurthy, Alekh Agarwal, John Langford
2021	J	`jnl`	Sparsity in Partially Controllable Linear Systems. CoRR Yonathan Efroni, Sham M. Kakade, Akshay Krishnamurthy, Cyril Zhang
2021	J	`jnl`	Trace Reconstruction: Generalized and Parameterized. IEEE Trans. Inf. Theory Akshay Krishnamurthy, Arya Mazumdar, Andrew McGregor, Soumyabrata Pal
2021	J	`jnl`	Universal and data-adaptive algorithms for model selection in linear contextual bandits. CoRR Vidya Muthukumar, Akshay Krishnamurthy
2020	A*	`conf`	Adaptive Estimator Selection for Off-Policy Evaluation. ICML Yi Su, Pavithra Srinath, Akshay Krishnamurthy
2020	J	`jnl`	Adaptive Estimator Selection for Off-Policy Evaluation. CoRR Yi Su, Pavithra Srinath, Akshay Krishnamurthy
2020	B	`conf`	Algebraic and Analytic Approaches for Parameter Learning in Mixture Models. ALT Akshay Krishnamurthy, Arya Mazumdar, Andrew McGregor, Soumyabrata Pal
2020	J	`jnl`	Algebraic and Analytic Approaches for Parameter Learning in Mixture Models. CoRR Akshay Krishnamurthy, Arya Mazumdar, Andrew McGregor, Soumyabrata Pal
2020	J	`jnl`	Contextual Bandits with Continuous Actions: Smoothing, Zooming, and Adapting. J. Mach. Learn. Res. Akshay Krishnamurthy, John Langford, Aleksandrs Slivkins, Chicheng Zhang
2020	J	`jnl`	Contrastive estimation reveals topic posterior information to linear models. CoRR Christopher Tosh, Akshay Krishnamurthy, Daniel Hsu
2020	J	`jnl`	Contrastive learning, multi-view redundancy, and linear models. CoRR Christopher Tosh, Akshay Krishnamurthy, Daniel Hsu
2020	J	`jnl`	Corrupted Multidimensional Binary Search: Learning in the Presence of Irrational Agents. CoRR Akshay Krishnamurthy, Thodoris Lykouris, Chara Podimata
2020	A*	`conf`	Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Bounds. ICLR Jordan T. Ash, Chicheng Zhang, Akshay Krishnamurthy, John Langford, Alekh Agarwal
2020	A*	`conf`	Doubly robust off-policy evaluation with shrinkage. ICML Yi Su, Maria Dimakopoulou, Akshay Krishnamurthy, Miroslav Dudík
2020	A*	`conf`	Efficient Contextual Bandits with Continuous Actions. NeurIPS Maryam Majzoubi, Chicheng Zhang, Rajan Chari, Akshay Krishnamurthy, John Langford, Aleksandrs Slivkins
2020	J	`jnl`	Efficient Contextual Bandits with Continuous Actions. CoRR Maryam Majzoubi, Chicheng Zhang, Rajan Chari, Akshay Krishnamurthy, John Langford, Aleksandrs Slivkins
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	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`	Kinematic State Abstraction and Provably Efficient Rich-Observation Reinforcement Learning. ICML Dipendra Misra, Mikael Henaff, Akshay Krishnamurthy, John Langford
2020	A*	`conf`	Learning the Linear Quadratic Regulator from Nonlinear Observations. NeurIPS Zakaria Mhammedi, Dylan J. Foster, Max Simchowitz, Dipendra Misra, Wen Sun, Akshay Krishnamurthy, Alexander Rakhlin, John Langford
2020	J	`jnl`	Learning the Linear Quadratic Regulator from Nonlinear Observations. CoRR Zakaria Mhammedi, Dylan J. Foster, Max Simchowitz, Dipendra Misra, Wen Sun, Akshay Krishnamurthy, Alexander Rakhlin, John Langford
2020	A*	`conf`	Open Problem: Model Selection for Contextual Bandits. COLT Dylan J. Foster, Akshay Krishnamurthy, Haipeng Luo
2020	J	`jnl`	Open Problem: Model Selection for Contextual Bandits. CoRR Dylan J. Foster, Akshay Krishnamurthy, Haipeng Luo
2020	A*	`conf`	Private Reinforcement Learning with PAC and Regret Guarantees. ICML Giuseppe Vietri, Borja Balle, Akshay Krishnamurthy, Zhiwei Steven Wu
2020	J	`jnl`	Private Reinforcement Learning with PAC and Regret Guarantees. CoRR Giuseppe Vietri, Borja Balle, Akshay Krishnamurthy, Zhiwei Steven Wu
2020	A*	`conf`	Provably adaptive reinforcement learning in metric spaces. NeurIPS Tongyi Cao, Akshay Krishnamurthy
2020	J	`jnl`	Provably adaptive reinforcement learning in metric spaces. CoRR Tongyi Cao, Akshay Krishnamurthy
2020	A*	`conf`	Reward-Free Exploration for Reinforcement Learning. ICML Chi Jin, Akshay Krishnamurthy, Max Simchowitz, Tiancheng Yu
2020	J	`jnl`	Reward-Free Exploration for Reinforcement Learning. CoRR Chi Jin, Akshay Krishnamurthy, Max Simchowitz, Tiancheng Yu
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	J	`jnl`	Scalable Hierarchical Clustering with Tree Grafting. CoRR Nicholas Monath, Ari Kobren, Akshay Krishnamurthy, Michael R. Glass, Andrew McCallum
2019	J	`jnl`	Active Learning for Cost-Sensitive Classification. J. Mach. Learn. Res. Akshay Krishnamurthy, Alekh Agarwal, Tzu-Kuo Huang, Hal Daumé III, John Langford
2019	J	`jnl`	Contextual Bandits with Continuous Actions: Smoothing, Zooming, and Adapting. CoRR Akshay Krishnamurthy, John Langford, Aleksandrs Slivkins, Chicheng Zhang
2019	A*	`conf`	Contextual bandits with continuous actions: Smoothing, zooming, and adapting. COLT Akshay Krishnamurthy, John Langford, Aleksandrs Slivkins, Chicheng Zhang
2019	J	`jnl`	Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Bounds. CoRR Jordan T. Ash, Chicheng Zhang, Akshay Krishnamurthy, John Langford, Alekh Agarwal
2019	A*	`conf`	Disagreement-Based Combinatorial Pure Exploration: Sample Complexity Bounds and an Efficient Algorithm. COLT Tongyi Cao, Akshay Krishnamurthy
2019	J	`jnl`	Doubly robust off-policy evaluation with shrinkage. CoRR Yi Su, Maria Dimakopoulou, Akshay Krishnamurthy, Miroslav Dudík
2019	J	`jnl`	Kinematic State Abstraction and Provably Efficient Rich-Observation Reinforcement Learning. CoRR Dipendra Misra, Mikael Henaff, Akshay Krishnamurthy, John Langford
2019	A*	`conf`	Model Selection for Contextual Bandits. NeurIPS Dylan J. Foster, Akshay Krishnamurthy, Haipeng Luo
2019	J	`jnl`	Model selection for contextual bandits. CoRR Dylan J. Foster, Akshay Krishnamurthy, Haipeng Luo
2019	A*	`conf`	Model-based RL in Contextual Decision Processes: PAC bounds and Exponential Improvements over Model-free Approaches. COLT Wen Sun, Nan Jiang, Akshay Krishnamurthy, Alekh Agarwal, John Langford
2019	A*	`conf`	Myopic Posterior Sampling for Adaptive Goal Oriented Design of Experiments. ICML Kirthevasan Kandasamy, Willie Neiswanger, Reed Zhang, Akshay Krishnamurthy, Jeff Schneider, Barnabás Póczos
2019	J	`jnl`	Optimism in Reinforcement Learning with Generalized Linear Function Approximation. CoRR Yining Wang, Ruosong Wang, Simon S. Du, Akshay Krishnamurthy
2019	A*	`conf`	Provably efficient RL with Rich Observations via Latent State Decoding. ICML Simon S. Du, Akshay Krishnamurthy, Nan Jiang, Alekh Agarwal, Miroslav Dudík, John Langford
2019	J	`jnl`	Provably efficient RL with Rich Observations via Latent State Decoding. CoRR Simon S. Du, Akshay Krishnamurthy, Nan Jiang, Alekh Agarwal, Miroslav Dudík, John Langford
2019	J	`jnl`	Robust Dynamic Assortment Optimization in the Presence of Outlier Customers. CoRR Xi Chen, Akshay Krishnamurthy, Yining Wang
2019	A*	`conf`	Sample Complexity of Learning Mixture of Sparse Linear Regressions. NeurIPS Akshay Krishnamurthy, Arya Mazumdar, Andrew McGregor, Soumyabrata Pal
2019	J	`jnl`	Sample Complexity of Learning Mixtures of Sparse Linear Regressions. CoRR Akshay Krishnamurthy, Arya Mazumdar, Andrew McGregor, Soumyabrata Pal
2019	A*	`conf`	Scalable Hierarchical Clustering with Tree Grafting. KDD Nicholas Monath, Ari Kobren, Akshay Krishnamurthy, Michael R. Glass, Andrew McCallum
2019	A	`conf`	Trace Reconstruction: Generalized and Parameterized. ESA Akshay Krishnamurthy, Arya Mazumdar, Andrew McGregor, Soumyabrata Pal
2019	J	`jnl`	Trace Reconstruction: Generalized and Parameterized. CoRR Akshay Krishnamurthy, Arya Mazumdar, Andrew McGregor, Soumyabrata Pal
2018	A*	`conf`	Contextual bandits with surrogate losses: Margin bounds and efficient algorithms. NeurIPS Dylan J. Foster, Akshay Krishnamurthy
2018	J	`jnl`	Contextual bandits with surrogate losses: Margin bounds and efficient algorithms. CoRR Dylan J. Foster, Akshay Krishnamurthy
2018	J	`jnl`	Extreme Compressive Sampling for Covariance Estimation. IEEE Trans. Inf. Theory Martin Azizyan, Akshay Krishnamurthy, Aarti Singh
2018	—	`conf`	Go for a Walk and Arrive at the Answer: Reasoning Over Paths in Knowledge Bases using Reinforcement Learning. ICLR (Poster) Rajarshi Das, Shehzaad Dhuliawala, Manzil Zaheer, Luke Vilnis, Ishan Durugkar, Akshay Krishnamurthy, Alex Smola, Andrew McCallum
2018	J	`jnl`	Model-Based Reinforcement Learning in Contextual Decision Processes. CoRR Wen Sun, Nan Jiang, Akshay Krishnamurthy, Alekh Agarwal, John Langford
2018	J	`jnl`	Myopic Bayesian Design of Experiments via Posterior Sampling and Probabilistic Programming. CoRR Kirthevasan Kandasamy, Willie Neiswanger, Reed Zhang, Akshay Krishnamurthy, Jeff Schneider, Barnabás Póczos
2018	A*	`conf`	On Oracle-Efficient PAC RL with Rich Observations. NeurIPS Christoph Dann, Nan Jiang, Akshay Krishnamurthy, Alekh Agarwal, John Langford, Robert E. Schapire
2018	J	`jnl`	On Polynomial Time PAC Reinforcement Learning with Rich Observations. CoRR Christoph Dann, Nan Jiang, Akshay Krishnamurthy, Alekh Agarwal, John Langford, Robert E. Schapire
2018	A	`conf`	Parallelised Bayesian Optimisation via Thompson Sampling. AISTATS Kirthevasan Kandasamy, Akshay Krishnamurthy, Jeff Schneider, Barnabás Póczos
2018	A*	`conf`	Semiparametric Contextual Bandits. ICML Akshay Krishnamurthy, Zhiwei Steven Wu, Vasilis Syrgkanis
2018	J	`jnl`	Semiparametric Contextual Bandits. CoRR Akshay Krishnamurthy, Zhiwei Steven Wu, Vasilis Syrgkanis
2017	A*	`conf`	A Hierarchical Algorithm for Extreme Clustering. KDD Ari Kobren, Nicholas Monath, Akshay Krishnamurthy, Andrew McCallum
2017	A*	`conf`	Active Learning for Cost-Sensitive Classification. ICML Akshay Krishnamurthy, Alekh Agarwal, Tzu-Kuo Huang, Hal Daumé III, John Langford
2017	J	`jnl`	Active Learning for Cost-Sensitive Classification. CoRR Akshay Krishnamurthy, Alekh Agarwal, Tzu-Kuo Huang, Hal Daumé III, John Langford
2017	J	`jnl`	An Online Hierarchical Algorithm for Extreme Clustering. CoRR Ari Kobren, Nicholas Monath, Akshay Krishnamurthy, Andrew McCallum
2017	J	`jnl`	Asynchronous Parallel Bayesian Optimisation via Thompson Sampling. CoRR Kirthevasan Kandasamy, Akshay Krishnamurthy, Jeff G. Schneider, Barnabás Póczos
2017	A*	`conf`	Contextual Decision Processes with low Bellman rank are PAC-Learnable. ICML Nan Jiang, Akshay Krishnamurthy, Alekh Agarwal, John Langford, Robert E. Schapire
2017	J	`jnl`	Disagreement-based combinatorial pure exploration: Efficient algorithms and an analysis with localization. CoRR Tongyi Cao, Akshay Krishnamurthy
2017	—	`conf`	Go for a Walk and Arrive at the Answer: Reasoning Over Knowledge Bases with Reinforcement Learning. AKBC@NIPS Rajarshi Das, Shehzaad Dhuliawala, Manzil Zaheer, Luke Vilnis, Ishan Durugkar, Akshay Krishnamurthy, Alex Smola, Andrew McCallum
2017	J	`jnl`	Go for a Walk and Arrive at the Answer: Reasoning Over Paths in Knowledge Bases using Reinforcement Learning. CoRR Rajarshi Das, Shehzaad Dhuliawala, Manzil Zaheer, Luke Vilnis, Ishan Durugkar, Akshay Krishnamurthy, Alexander J. Smola, Andrew McCallum
2017	—	`conf`	Off-policy evaluation for slate recommendation. NIPS Adith Swaminathan, Akshay Krishnamurthy, Alekh Agarwal, Miroslav Dudík, John Langford, Damien Jose, Imed Zitouni
2017	A*	`conf`	Open Problem: First-Order Regret Bounds for Contextual Bandits. COLT Alekh Agarwal, Akshay Krishnamurthy, John Langford, Haipeng Luo, Robert E. Schapire
2016	J	`jnl`	Contextual Decision Processes with Low Bellman Rank are PAC-Learnable. CoRR Nan Jiang, Akshay Krishnamurthy, Alekh Agarwal, John Langford, Robert E. Schapire
2016	—	`conf`	Contextual semibandits via supervised learning oracles. NIPS Akshay Krishnamurthy, Alekh Agarwal, Miroslav Dudík
2016	J	`jnl`	Contextual-MDPs for PAC-Reinforcement Learning with Rich Observations. CoRR Akshay Krishnamurthy, Alekh Agarwal, John Langford
2016	A*	`conf`	Efficient Algorithms for Adversarial Contextual Learning. ICML Vasilis Syrgkanis, Akshay Krishnamurthy, Robert E. Schapire
2016	J	`jnl`	Efficient Algorithms for Adversarial Contextual Learning. CoRR Vasilis Syrgkanis, Akshay Krishnamurthy, Robert E. Schapire
2016	J	`jnl`	Exploratory Gradient Boosting for Reinforcement Learning in Complex Domains. CoRR David Abel, Alekh Agarwal, Fernando Diaz, Akshay Krishnamurthy, Robert E. Schapire
2016	—	`conf`	Improved Regret Bounds for Oracle-Based Adversarial Contextual Bandits. NIPS Vasilis Syrgkanis, Haipeng Luo, Akshay Krishnamurthy, Robert E. Schapire
2016	J	`jnl`	Improved Regret Bounds for Oracle-Based Adversarial Contextual Bandits. CoRR Vasilis Syrgkanis, Haipeng Luo, Akshay Krishnamurthy, Robert E. Schapire
2016	B	`conf`	Minimax structured normal means inference. ISIT Akshay Krishnamurthy
2016	J	`jnl`	Off-policy evaluation for slate recommendation. CoRR Adith Swaminathan, Akshay Krishnamurthy, Alekh Agarwal, Miroslav Dudík, John Langford, Damien Jose, Imed Zitouni
2016	—	`conf`	PAC Reinforcement Learning with Rich Observations. NIPS Akshay Krishnamurthy, Alekh Agarwal, John Langford
2015	J	`jnl`	Efficient Contextual Semi-Bandit Learning. CoRR Akshay Krishnamurthy, Alekh Agarwal, Miroslav Dudík
2015	J	`jnl`	Extreme Compressive Sampling for Covariance Estimation. CoRR Martin Azizyan, Akshay Krishnamurthy, Aarti Singh
2015	J	`jnl`	Learning to Search Better Than Your Teacher. CoRR Kai-Wei Chang, Akshay Krishnamurthy, Alekh Agarwal, Hal Daumé III, John Langford
2015	A*	`conf`	Learning to Search Better than Your Teacher. ICML Kai-Wei Chang, Akshay Krishnamurthy, Alekh Agarwal, Hal Daumé III, John Langford
2015	J	`jnl`	Minimaxity in Structured Normal Means Inference. CoRR Akshay Krishnamurthy
2015	—	`conf`	Nonparametric von Mises Estimators for Entropies, Divergences and Mutual Informations. NIPS Kirthevasan Kandasamy, Akshay Krishnamurthy, Barnabás Póczos, Larry A. Wasserman, James M. Robins
2015	A	`conf`	On Estimating L22 Divergence. AISTATS Akshay Krishnamurthy, Kirthevasan Kandasamy, Barnabás Póczos, Larry A. Wasserman
2014	J	`jnl`	Influence Functions for Machine Learning: Nonparametric Estimators for Entropies, Divergences and Mutual Informations. CoRR Kirthevasan Kandasamy, Akshay Krishnamurthy, Barnabás Póczos, Larry A. Wasserman, James M. Robins
2014	A*	`conf`	Nonparametric Estimation of Renyi Divergence and Friends. ICML Akshay Krishnamurthy, Kirthevasan Kandasamy, Barnabás Póczos, Larry A. Wasserman
2014	J	`jnl`	On the Power of Adaptivity in Matrix Completion and Approximation. CoRR Akshay Krishnamurthy, Aarti Singh
2014	J	`jnl`	Subspace Learning from Extremely Compressed Measurements. CoRR Akshay Krishnamurthy, Martin Azizyan, Aarti Singh
2014	Misc	`conf`	Subspace learning from extremely compressed measurements. ACSSC Martin Azizyan, Akshay Krishnamurthy, Aarti Singh
2013	A	`conf`	Detecting Activations over Graphs using Spanning Tree Wavelet Bases. AISTATS James Sharpnack, Aarti Singh, Akshay Krishnamurthy
2013	—	`conf`	Low-Rank Matrix and Tensor Completion via Adaptive Sampling. NIPS Akshay Krishnamurthy, Aarti Singh
2013	—	`conf`	Near-optimal Anomaly Detection in Graphs using Lovasz Extended Scan Statistic. NIPS James Sharpnack, Akshay Krishnamurthy, Aarti Singh
2013	J	`jnl`	Recovering Graph-Structured Activations using Adaptive Compressive Measurements CoRR Akshay Krishnamurthy, James Sharpnack, Aarti Singh
2013	Misc	`conf`	Recovering graph-structured activations using adaptive compressive measurements. ACSSC Akshay Krishnamurthy, James Sharpnack, Aarti Singh
2012	J	`jnl`	Detecting Activations over Graphs using Spanning Tree Wavelet Bases CoRR Akshay Krishnamurthy, James Sharpnack, Aarti Singh
2012	J	`jnl`	Efficient Active Algorithms for Hierarchical Clustering CoRR Akshay Krishnamurthy, Sivaraman Balakrishnan, Min Xu, Aarti Singh
2012	A*	`conf`	Efficient Active Algorithms for Hierarchical Clustering. ICML Akshay Krishnamurthy, Sivaraman Balakrishnan, Min Xu, Aarti Singh
2012	A*	`conf`	Robust multi-source network tomography using selective probes. INFOCOM Akshay Krishnamurthy, Aarti Singh
2011	—	`conf`	Noise Thresholds for Spectral Clustering. NIPS Sivaraman Balakrishnan, Min Xu, Akshay Krishnamurthy, Aarti Singh
2010	A*	`conf`	Fine-grained privilege separation for web applications. WWW Akshay Krishnamurthy, Adrian Mettler, David A. Wagner