Jason D. Lee - RankMe

309 papers A* 105A 11C 2Misc 1Journal 174Unranked 16

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Coverage Improvement and Fast Convergence of On-policy Preference Learning. CoRR Juno Kim, Jihun Yun, Jason D. Lee, Kwang-Sung Jun
2026	J	`jnl`	Improved high-dimensional estimation with Langevin dynamics and stochastic weight averaging. CoRR Stanley Wei, Alex Damian, Jason D. Lee
2026	J	`jnl`	Provable Learning of Random Hierarchy Models and Hierarchical Shallow-to-Deep Chaining. CoRR Yunwei Ren, Yatin Dandi, Florent Krzakala, Jason D. Lee
2026	J	`jnl`	Sharp Capacity Scaling of Spectral Optimizers in Learning Associative Memory. CoRR Juno Kim, Eshaan Nichani, Denny Wu, Alberto Bietti, Jason D. Lee
2026	J	`jnl`	Statistical Learning Theory in Lean 4: Empirical Processes from Scratch. CoRR Yuanhe Zhang, Jason D. Lee, Fanghui Liu
2025	J	`jnl`	Accelerating RL for LLM Reasoning with Optimal Advantage Regression. CoRR Kianté Brantley, Mingyu Chen, Zhaolin Gao, Jason D. Lee, Wen Sun, Wenhao Zhan, Xuezhou Zhang
2025	A*	`conf`	Anytime Acceleration of Gradient Descent. COLT Zihan Zhang, Jason D. Lee, Simon S. Du, Yuxin Chen
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	J	`jnl`	DAG-Math: Graph-Guided Mathematical Reasoning in LLMs. CoRR Yuanhe Zhang, Ilja Kuzborskij, Jason D. Lee, Chenlei Leng, Fanghui Liu
2025	A*	`conf`	Discrepancies are Virtue: Weak-to-Strong Generalization through Lens of Intrinsic Dimension. ICML Yijun Dong, Yicheng Li, Yunai Li, Jason D. Lee, Qi Lei
2025	J	`jnl`	Discrepancies are Virtue: Weak-to-Strong Generalization through Lens of Intrinsic Dimension. CoRR Yijun Dong, Yicheng Li, Yunai Li, Jason D. Lee, Qi Lei
2025	J	`jnl`	Emergence and scaling laws in SGD learning of shallow neural networks. CoRR Yunwei Ren, Eshaan Nichani, Denny Wu, Jason D. Lee
2025	A*	`conf`	Exploiting Structure in Offline Multi-Agent RL: The Benefits of Low Interaction Rank. ICLR Wenhao Zhan, Scott Fujimoto, Zheqing Zhu, Jason D. Lee, Daniel Jiang, Yonathan Efroni
2025	A	`conf`	How Well Can Transformers Emulate In-Context Newton's Method? AISTATS Angeliki Giannou, Liu Yang, Tianhao Wang, Dimitris Papailiopoulos, Jason D. Lee
2025	A*	`conf`	Learning Compositional Functions with Transformers from Easy-to-Hard Data. COLT Zixuan Wang, Eshaan Nichani, Alberto Bietti, Alex Damian, Daniel Hsu, Jason D. Lee, Denny Wu
2025	J	`jnl`	Learning Compositional Functions with Transformers from Easy-to-Hard Data. CoRR Zixuan Wang, Eshaan Nichani, Alberto Bietti, Alex Damian, Daniel Hsu, Jason D. Lee, Denny Wu
2025	A*	`conf`	Learning Hierarchical Polynomials of Multiple Nonlinear Features. ICLR Hengyu Fu, Zihao Wang, Eshaan Nichani, Jason D. Lee
2025	A*	`conf`	Metastable Dynamics of Chain-of-Thought Reasoning: Provable Benefits of Search, RL and Distillation. ICML Juno Kim, Denny Wu, Jason D. Lee, Taiji Suzuki
2025	A*	`conf`	Minimax Optimal Regret Bound for Reinforcement Learning with Trajectory Feedback. ICML Zihan Zhang, Yuxin Chen, Jason D. Lee, Simon Shaolei Du, Ruosong Wang
2025	J	`jnl`	Neural Networks Learn Generic Multi-Index Models Near Information-Theoretic Limit. CoRR Bohan Zhang, Zihao Wang, Hengyu Fu, Jason D. Lee
2025	J	`jnl`	On the Statistical Query Complexity of Learning Semiautomata: a Random Walk Approach. CoRR George Giapitzakis, Kimon Fountoulakis, Eshaan Nichani, Jason D. Lee
2025	J	`jnl`	Optimal Multi-Distribution Learning. J. ACM Zihan Zhang, Wenhao Zhan, Yuxin Chen, Simon S. Du, Jason D. Lee
2025	J	`jnl`	Quantitative Bounds for Length Generalization in Transformers. CoRR Zachary Izzo, Eshaan Nichani, Jason D. Lee
2025	A*	`conf`	Regressing the Relative Future: Efficient Policy Optimization for Multi-turn RLHF. ICLR Zhaolin Gao, Wenhao Zhan, Jonathan Daniel Chang, Gokul Swamy, Kianté Brantley, Jason D. Lee, Wen Sun
2025	A*	`conf`	Rethinking Addressing in Language Models via Contextualized Equivariant Positional Encoding. ICML Jiajun Zhu, Peihao Wang, Ruisi Cai, Jason D. Lee, Pan Li, Zhangyang Wang
2025	J	`jnl`	Rethinking Addressing in Language Models via Contexualized Equivariant Positional Encoding. CoRR Jiajun Zhu, Peihao Wang, Ruisi Cai, Jason D. Lee, Pan Li, Zhangyang Wang
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	J	`jnl`	Settling the Sample Complexity of Online Reinforcement Learning. J. ACM Zihan Zhang, Yuxin Chen, Jason D. Lee, Simon S. Du
2025	J	`jnl`	Task Diversity Shortens the In-Context Learning Plateau. Trans. Mach. Learn. Res. Jaeyeon Kim, Sehyun Kwon, Joo Young Choi, Jongho Park, Jaewoong Cho, Jason D. Lee, Ernest K. Ryu
2025	J	`jnl`	The Generative Leap: Sharp Sample Complexity for Efficiently Learning Gaussian Multi-Index Models. CoRR Alex Damian, Jason D. Lee, Joan Bruna
2025	A*	`conf`	Transformers Learn to Implement Multi-step Gradient Descent with Chain of Thought. ICLR Jianhao Huang, Zixuan Wang, Jason D. Lee
2025	J	`jnl`	Transformers Learn to Implement Multi-step Gradient Descent with Chain of Thought. CoRR Jianhao Huang, Zixuan Wang, Jason D. Lee
2025	A*	`conf`	Transformers Provably Learn Two-Mixture of Linear Classification via Gradient Flow. ICLR Hongru Yang, Zhangyang Wang, Jason D. Lee, Yingbin Liang
2025	A*	`conf`	Understanding Factual Recall in Transformers via Associative Memories. ICLR Eshaan Nichani, Jason D. Lee, Alberto Bietti
2025	A*	`conf`	Understanding Optimization in Deep Learning with Central Flows. ICLR Jeremy Cohen, Alex Damian, Ameet Talwalkar, J. Zico Kolter, Jason D. Lee
2025	J	`jnl`	What Makes a Reward Model a Good Teacher? An Optimization Perspective. CoRR Noam Razin, Zixuan Wang, Hubert Strauss, Stanley Wei, Jason D. Lee, Sanjeev Arora
2025	J	`jnl`	What One Cannot, Two Can: Two-Layer Transformers Provably Represent Induction Heads on Any-Order Markov Chains. CoRR Chanakya Ekbote, Marco Bondaschi, Nived Rajaraman, Jason D. Lee, Michael Gastpar, Ashok Vardhan Makkuva, Paul Pu Liang
2024	A*	`conf`	An Information-Theoretic Analysis of In-Context Learning. ICML Hong Jun Jeon, Jason D. Lee, Qi Lei, Benjamin Van Roy
2024	J	`jnl`	An Information-Theoretic Analysis of In-Context Learning. CoRR Hong Jun Jeon, Jason D. Lee, Qi Lei, Benjamin Van Roy
2024	J	`jnl`	Anytime Acceleration of Gradient Descent. CoRR Zihan Zhang, Jason D. Lee, Simon S. Du, Yuxin Chen
2024	A*	`conf`	BitDelta: Your Fine-Tune May Only Be Worth One Bit. NeurIPS James Liu, Guangxuan Xiao, Kai Li, Jason D. Lee, Song Han, Tri Dao, Tianle Cai
2024	J	`jnl`	BitDelta: Your Fine-Tune May Only Be Worth One Bit. CoRR James Liu, Guangxuan Xiao, Kai Li, Jason D. Lee, Song Han, Tri Dao, Tianle Cai
2024	A*	`conf`	Computational-Statistical Gaps in Gaussian Single-Index Models (Extended Abstract). COLT Alex Damian, Loucas Pillaud-Vivien, Jason D. Lee, Joan Bruna
2024	J	`jnl`	Computational-Statistical Gaps in Gaussian Single-Index Models. CoRR Alex Damian, Loucas Pillaud-Vivien, Jason D. Lee, Joan Bruna
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`	Dataset Reset Policy Optimization for RLHF. CoRR Jonathan D. Chang, Wenhao Zhan, Owen Oertell, Kianté Brantley, Dipendra Misra, Jason D. Lee, Wen Sun
2024	A*	`conf`	Dichotomy of Early and Late Phase Implicit Biases Can Provably Induce Grokking. ICLR Kaifeng Lyu, Jikai Jin, Zhiyuan Li, Simon Shaolei Du, Jason D. Lee, Wei Hu
2024	J	`jnl`	Exploiting Structure in Offline Multi-Agent RL: The Benefits of Low Interaction Rank. CoRR Wenhao Zhan, Scott Fujimoto, Zheqing Zhu, Jason D. Lee, Daniel R. Jiang, Yonathan Efroni
2024	A*	`conf`	Horizon-Free Regret for Linear Markov Decision Processes. ICLR Zihan Zhang, Jason D. Lee, Yuxin Chen, Simon Shaolei Du
2024	J	`jnl`	Horizon-Free Regret for Linear Markov Decision Processes. CoRR Zihan Zhang, Jason D. Lee, Yuxin Chen, Simon S. Du
2024	A*	`conf`	How Transformers Learn Causal Structure with Gradient Descent. ICML Eshaan Nichani, Alex Damian, Jason D. Lee
2024	J	`jnl`	How Transformers Learn Causal Structure with Gradient Descent. CoRR Eshaan Nichani, Alex Damian, Jason D. Lee
2024	J	`jnl`	How Well Can Transformers Emulate In-context Newton's Method? CoRR Angeliki Giannou, Liu Yang, Tianhao Wang, Dimitris Papailiopoulos, Jason D. Lee
2024	J	`jnl`	Learning Hierarchical Polynomials of Multiple Nonlinear Features with Three-Layer Networks. CoRR Hengyu Fu, Zihao Wang, Eshaan Nichani, Jason D. Lee
2024	A*	`conf`	Learning Hierarchical Polynomials with Three-Layer Neural Networks. ICLR Zihao Wang, Eshaan Nichani, Jason D. Lee
2024	J	`jnl`	Learning Orthogonal Multi-Index Models: A Fine-Grained Information Exponent Analysis. CoRR Yunwei Ren, Jason D. Lee
2024	A*	`conf`	Learning and Transferring Sparse Contextual Bigrams with Linear Transformers. NeurIPS Yunwei Ren, Zixuan Wang, Jason D. Lee
2024	J	`jnl`	Learning and Transferring Sparse Contextual Bigrams with Linear Transformers. CoRR Yunwei Ren, Zixuan Wang, Jason D. Lee
2024	A*	`conf`	LoRA Training in the NTK Regime has No Spurious Local Minima. ICML Uijeong Jang, Jason D. Lee, Ernest K. Ryu
2024	J	`jnl`	LoRA Training in the NTK Regime has No Spurious Local Minima. CoRR Uijeong Jang, Jason D. Lee, Ernest K. Ryu
2024	A*	`conf`	Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads. ICML Tianle Cai, Yuhong Li, Zhengyang Geng, Hongwu Peng, Jason D. Lee, Deming Chen, Tri Dao
2024	J	`jnl`	Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads. CoRR Tianle Cai, Yuhong Li, Zhengyang Geng, Hongwu Peng, Jason D. Lee, Deming Chen, Tri Dao
2024	J	`jnl`	Neural Temporal Difference and Q Learning Provably Converge to Global Optima. Math. Oper. Res. Qi Cai, Zhuoran Yang, Jason D. Lee, Zhaoran Wang
2024	A*	`conf`	Neural network learns low-dimensional polynomials with SGD near the information-theoretic limit. NeurIPS Jason D. Lee, Kazusato Oko, Taiji Suzuki, Denny Wu
2024	J	`jnl`	Neural network learns low-dimensional polynomials with SGD near the information-theoretic limit. CoRR Jason D. Lee, Kazusato Oko, Taiji Suzuki, Denny Wu
2024	A*	`conf`	Optimal Multi-Distribution Learning. COLT Zihan Zhang, Wenhao Zhan, Yuxin Chen, Simon S. Du, Jason D. Lee
2024	A*	`conf`	Provable Offline Preference-Based Reinforcement Learning. ICLR Wenhao Zhan, Masatoshi Uehara, Nathan Kallus, Jason D. Lee, Wen Sun
2024	A*	`conf`	Provable Reward-Agnostic Preference-Based Reinforcement Learning. ICLR Wenhao Zhan, Masatoshi Uehara, Wen Sun, Jason D. Lee
2024	A*	`conf`	Provably Efficient CVaR RL in Low-rank MDPs. ICLR Yulai Zhao, Wenhao Zhan, Xiaoyan Hu, Ho-fung Leung, Farzan Farnia, Wen Sun, Jason D. Lee
2024	A*	`conf`	REBEL: Reinforcement Learning via Regressing Relative Rewards. NeurIPS Zhaolin Gao, Jonathan D. Chang, Wenhao Zhan, Owen Oertell, Gokul Swamy, Kianté Brantley, Thorsten Joachims, Drew Bagnell, Jason D. Lee, Wen Sun
2024	J	`jnl`	REBEL: Reinforcement Learning via Regressing Relative Rewards. CoRR Zhaolin Gao, Jonathan D. Chang, Wenhao Zhan, Owen Oertell, Gokul Swamy, Kianté Brantley, Thorsten Joachims, J. Andrew Bagnell, Jason D. Lee, Wen Sun
2024	—	`conf`	REST: Retrieval-Based Speculative Decoding. NAACL-HLT Zhenyu He, Zexuan Zhong, Tianle Cai, Jason D. Lee, Di He
2024	J	`jnl`	Regressing the Relative Future: Efficient Policy Optimization for Multi-turn RLHF. CoRR Zhaolin Gao, Wenhao Zhan, Jonathan D. Chang, Gokul Swamy, Kianté Brantley, Jason D. Lee, Wen Sun
2024	A*	`conf`	Revisiting Zeroth-Order Optimization for Memory-Efficient LLM Fine-Tuning: A Benchmark. ICML Yihua Zhang, Pingzhi Li, Junyuan Hong, Jiaxiang Li, Yimeng Zhang, Wenqing Zheng, Pin-Yu Chen, Jason D. Lee, Wotao Yin, Mingyi Hong, Zhangyang Wang, Sijia Liu, Tianlong Chen
2024	J	`jnl`	Revisiting Zeroth-Order Optimization for Memory-Efficient LLM Fine-Tuning: A Benchmark. CoRR Yihua Zhang, Pingzhi Li, Junyuan Hong, Jiaxiang Li, Yimeng Zhang, Wenqing Zheng, Pin-Yu Chen, Jason D. Lee, Wotao Yin, Mingyi Hong, Zhangyang Wang, Sijia Liu, Tianlong Chen
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`	Settling the sample complexity of online reinforcement learning. COLT Zihan Zhang, Yuxin Chen, Jason D. Lee, Simon S. Du
2024	A*	`conf`	Stochastic Zeroth-Order Optimization under Strongly Convexity and Lipschitz Hessian: Minimax Sample Complexity. NeurIPS Qian Yu, Yining Wang, Baihe Huang, Qi Lei, Jason D. Lee
2024	J	`jnl`	Stochastic Zeroth-Order Optimization under Strongly Convexity and Lipschitz Hessian: Minimax Sample Complexity. CoRR Qian Yu, Yining Wang, Baihe Huang, Qi Lei, Jason D. Lee
2024	J	`jnl`	Task Diversity Shortens the ICL Plateau. CoRR Jaeyeon Kim, Sehyun Kwon, Joo Young Choi, Jongho Park, Jaewoong Cho, Jason D. Lee, Ernest K. Ryu
2024	A*	`conf`	Teaching Arithmetic to Small Transformers. ICLR Nayoung Lee, Kartik Sreenivasan, Jason D. Lee, Kangwook Lee, Dimitris Papailiopoulos
2024	A*	`conf`	Transformers Provably Learn Sparse Token Selection While Fully-Connected Nets Cannot. ICML Zixuan Wang, Stanley Wei, Daniel Hsu, Jason D. Lee
2024	J	`jnl`	Transformers Provably Learn Sparse Token Selection While Fully-Connected Nets Cannot. CoRR Zixuan Wang, Stanley Wei, Daniel Hsu, Jason D. Lee
2024	J	`jnl`	Understanding Factual Recall in Transformers via Associative Memories. CoRR Eshaan Nichani, Jason D. Lee, Alberto Bietti
2024	J	`jnl`	Understanding Optimization in Deep Learning with Central Flows. CoRR Jeremy Cohen, Alex Damian, Ameet Talwalkar, Zico Kolter, Jason D. Lee
2023	A*	`conf`	Can We Find Nash Equilibria at a Linear Rate in Markov Games? ICLR Zhuoqing Song, Jason D. Lee, Zhuoran Yang
2023	J	`jnl`	Can We Find Nash Equilibria at a Linear Rate in Markov Games? CoRR Zhuoqing Song, Jason D. Lee, Zhuoran Yang
2023	A*	`conf`	Computationally Efficient PAC RL in POMDPs with Latent Determinism and Conditional Embeddings. ICML Masatoshi Uehara, Ayush Sekhari, Jason D. Lee, Nathan Kallus, Wen Sun
2023	A*	`conf`	Decentralized Optimistic Hyperpolicy Mirror Descent: Provably No-Regret Learning in Markov Games. ICLR Wenhao Zhan, Jason D. Lee, Zhuoran Yang
2023	J	`jnl`	Dichotomy of Early and Late Phase Implicit Biases Can Provably Induce Grokking. CoRR Kaifeng Lyu, Jikai Jin, Zhiyuan Li, Simon S. Du, Jason D. Lee, Wei Hu
2023	A*	`conf`	Efficient displacement convex optimization with particle gradient descent. ICML Hadi Daneshmand, Jason D. Lee, Chi Jin
2023	J	`jnl`	Efficient displacement convex optimization with particle gradient descent. CoRR Hadi Daneshmand, Jason D. Lee, Chi Jin
2023	A*	`conf`	Fine-Tuning Language Models with Just Forward Passes. NeurIPS Sadhika Malladi, Tianyu Gao, Eshaan Nichani, Alex Damian, Jason D. Lee, Danqi Chen, Sanjeev Arora
2023	J	`jnl`	Fine-Tuning Language Models with Just Forward Passes. CoRR Sadhika Malladi, Tianyu Gao, Eshaan Nichani, Alex Damian, Jason D. Lee, Danqi Chen, Sanjeev Arora
2023	J	`jnl`	How to Query Human Feedback Efficiently in RL? CoRR Wenhao Zhan, Masatoshi Uehara, Wen Sun, Jason D. Lee
2023	A*	`conf`	Implicit Bias of Gradient Descent for Logistic Regression at the Edge of Stability. NeurIPS Jingfeng Wu, Vladimir Braverman, Jason D. Lee
2023	J	`jnl`	Implicit Bias of Gradient Descent for Logistic Regression at the Edge of Stability. CoRR Jingfeng Wu, Vladimir Braverman, Jason D. Lee
2023	J	`jnl`	Learning Hierarchical Polynomials with Three-Layer Neural Networks. CoRR Zihao Wang, Eshaan Nichani, Jason D. Lee
2023	A*	`conf`	Local Optimization Achieves Global Optimality in Multi-Agent Reinforcement Learning. ICML Yulai Zhao, Zhuoran Yang, Zhaoran Wang, Jason D. Lee
2023	J	`jnl`	Local Optimization Achieves Global Optimality in Multi-Agent Reinforcement Learning. CoRR Yulai Zhao, Zhuoran Yang, Zhaoran Wang, Jason D. Lee
2023	A*	`conf`	Looped Transformers as Programmable Computers. ICML Angeliki Giannou, Shashank Rajput, Jy-yong Sohn, Kangwook Lee, Jason D. Lee, Dimitris Papailiopoulos
2023	J	`jnl`	Looped Transformers as Programmable Computers. CoRR Angeliki Giannou, Shashank Rajput, Jy-yong Sohn, Kangwook Lee, Jason D. Lee, Dimitris S. Papailiopoulos
2023	A*	`conf`	Offline Minimax Soft-Q-learning Under Realizability and Partial Coverage. NeurIPS Masatoshi Uehara, Nathan Kallus, Jason D. Lee, Wen Sun
2023	J	`jnl`	Optimal Multi-Distribution Learning. CoRR Zihan Zhang, Wenhao Zhan, Yuxin Chen, Simon S. Du, Jason D. Lee
2023	A	`conf`	Optimal Sample Complexity Bounds for Non-convex Optimization under Kurdyka-Lojasiewicz Condition. AISTATS Qian Yu, Yining Wang, Baihe Huang, Qi Lei, Jason D. Lee
2023	A*	`conf`	PAC Reinforcement Learning for Predictive State Representations. ICLR Wenhao Zhan, Masatoshi Uehara, Wen Sun, Jason D. Lee
2023	J	`jnl`	Policy Mirror Descent for Regularized Reinforcement Learning: A Generalized Framework with Linear Convergence. SIAM J. Optim. Wenhao Zhan, Shicong Cen, Baihe Huang, Yuxin Chen, Jason D. Lee, Yuejie Chi
2023	A*	`conf`	Provable Guarantees for Nonlinear Feature Learning in Three-Layer Neural Networks. NeurIPS Eshaan Nichani, Alex Damian, Jason D. Lee
2023	J	`jnl`	Provable Guarantees for Nonlinear Feature Learning in Three-Layer Neural Networks. CoRR Eshaan Nichani, Alex Damian, Jason D. Lee
2023	A	`conf`	Provable Hierarchy-Based Meta-Reinforcement Learning. AISTATS Kurtland Chua, Qi Lei, Jason D. Lee
2023	J	`jnl`	Provable Offline Reinforcement Learning with Human Feedback. CoRR Wenhao Zhan, Masatoshi Uehara, Nathan Kallus, Jason D. Lee, Wen Sun
2023	J	`jnl`	Provably Efficient CVaR RL in Low-rank MDPs. CoRR Yulai Zhao, Wenhao Zhan, Xiaoyan Hu, Ho-fung Leung, Farzan Farnia, Wen Sun, Jason D. Lee
2023	A	`conf`	Provably Efficient Reinforcement Learning via Surprise Bound. AISTATS Hanlin Zhu, Ruosong Wang, Jason D. Lee
2023	J	`jnl`	Provably Efficient Reinforcement Learning via Surprise Bound. CoRR Hanlin Zhu, Ruosong Wang, Jason D. Lee
2023	J	`jnl`	REST: Retrieval-Based Speculative Decoding. CoRR Zhenyu He, Zexuan Zhong, Tianle Cai, Jason D. Lee, Di He
2023	J	`jnl`	Refined Value-Based Offline RL under Realizability and Partial Coverage. CoRR Masatoshi Uehara, Nathan Kallus, Jason D. Lee, Wen Sun
2023	—	`conf`	Regret Guarantees for Online Deep Control. L4DC Xinyi Chen, Edgar Minasyan, Jason D. Lee, Elad Hazan
2023	J	`jnl`	Reward Collapse in Aligning Large Language Models. CoRR Ziang Song, Tianle Cai, Jason D. Lee, Weijie J. Su
2023	A*	`conf`	Reward-agnostic Fine-tuning: Provable Statistical Benefits of Hybrid Reinforcement Learning. NeurIPS Gen Li, Wenhao Zhan, Jason D. Lee, Yuejie Chi, Yuxin Chen
2023	J	`jnl`	Reward-agnostic Fine-tuning: Provable Statistical Benefits of Hybrid Reinforcement Learning. CoRR Gen Li, Wenhao Zhan, Jason D. Lee, Yuejie Chi, Yuxin Chen
2023	A*	`conf`	Sample Complexity for Quadratic Bandits: Hessian Dependent Bounds and Optimal Algorithms. NeurIPS Qian Yu, Yining Wang, Baihe Huang, Qi Lei, Jason D. Lee
2023	J	`jnl`	Sample Complexity for Quadratic Bandits: Hessian Dependent Bounds and Optimal Algorithms. CoRR Qian Yu, Yining Wang, Baihe Huang, Qi Lei, Jason D. Lee
2023	J	`jnl`	Scaling In-Context Demonstrations with Structured Attention. CoRR Tianle Cai, Kaixuan Huang, Jason D. Lee, Mengdi Wang
2023	A*	`conf`	Self-Stabilization: The Implicit Bias of Gradient Descent at the Edge of Stability. ICLR Alex Damian, Eshaan Nichani, Jason D. Lee
2023	J	`jnl`	Settling the Sample Complexity of Online Reinforcement Learning. CoRR Zihan Zhang, Yuxin Chen, Jason D. Lee, Simon S. Du
2023	A*	`conf`	Smoothing the Landscape Boosts the Signal for SGD: Optimal Sample Complexity for Learning Single Index Models. NeurIPS Alex Damian, Eshaan Nichani, Rong Ge, Jason D. Lee
2023	J	`jnl`	Smoothing the Landscape Boosts the Signal for SGD: Optimal Sample Complexity for Learning Single Index Models. CoRR Alex Damian, Eshaan Nichani, Rong Ge, Jason D. Lee
2023	J	`jnl`	Solving Robust MDPs through No-Regret Dynamics. CoRR Etash Kumar Guha, Jason D. Lee
2023	J	`jnl`	Teaching Arithmetic to Small Transformers. CoRR Nayoung Lee, Kartik Sreenivasan, Jason D. Lee, Kangwook Lee, Dimitris Papailiopoulos
2023	J	`jnl`	Towards Optimal Statistical Watermarking. CoRR Baihe Huang, Banghua Zhu, Hanlin Zhu, Jason D. Lee, Jiantao Jiao, Michael I. Jordan
2023	A*	`conf`	Understanding Incremental Learning of Gradient Descent: A Fine-grained Analysis of Matrix Sensing. ICML Jikai Jin, Zhiyuan Li, Kaifeng Lyu, Simon Shaolei Du, Jason D. Lee
2023	J	`jnl`	Understanding Incremental Learning of Gradient Descent: A Fine-grained Analysis of Matrix Sensing. CoRR Jikai Jin, Zhiyuan Li, Kaifeng Lyu, Simon S. Du, Jason D. Lee
2022	Misc	`conf`	Competitive Multi-Agent Reinforcement Learning with Self-Supervised Representation. ICASSP DiJia Su, Jason D. Lee, John M. Mulvey, H. Vincent Poor
2022	J	`jnl`	Computationally Efficient PAC RL in POMDPs with Latent Determinism and Conditional Embeddings. CoRR Masatoshi Uehara, Ayush Sekhari, Jason D. Lee, Nathan Kallus, Wen Sun
2022	J	`jnl`	Decentralized Optimistic Hyperpolicy Mirror Descent: Provably No-Regret Learning in Markov Games. CoRR Wenhao Zhan, Jason D. Lee, Zhuoran Yang
2022	A*	`conf`	From Gradient Flow on Population Loss to Learning with Stochastic Gradient Descent. NeurIPS Christopher De Sa, Satyen Kale, Jason D. Lee, Ayush Sekhari, Karthik Sridharan
2022	J	`jnl`	From Gradient Flow on Population Loss to Learning with Stochastic Gradient Descent. CoRR Satyen Kale, Jason D. Lee, Chris De Sa, Ayush Sekhari, Karthik Sridharan
2022	A*	`conf`	Identifying good directions to escape the NTK regime and efficiently learn low-degree plus sparse polynomials. NeurIPS Eshaan Nichani, Yu Bai, Jason D. Lee
2022	J	`jnl`	Identifying good directions to escape the NTK regime and efficiently learn low-degree plus sparse polynomials. CoRR Eshaan Nichani, Yu Bai, Jason D. Lee
2022	A*	`conf`	Implicit Bias of Gradient Descent on Reparametrized Models: On Equivalence to Mirror Descent. NeurIPS Zhiyuan Li, Tianhao Wang, Jason D. Lee, Sanjeev Arora
2022	J	`jnl`	Implicit Bias of Gradient Descent on Reparametrized Models: On Equivalence to Mirror Descent. CoRR Zhiyuan Li, Tianhao Wang, Jason D. Lee, Sanjeev Arora
2022	J	`jnl`	Nearly Minimax Algorithms for Linear Bandits with Shared Representation. CoRR Jiaqi Yang, Qi Lei, Jason D. Lee, Simon S. Du
2022	A*	`conf`	Neural Networks can Learn Representations with Gradient Descent. COLT Alexandru Damian, Jason D. Lee, Mahdi Soltanolkotabi
2022	J	`jnl`	Neural Networks can Learn Representations with Gradient Descent. CoRR Alex Damian, Jason D. Lee, Mahdi Soltanolkotabi
2022	A*	`conf`	Offline Reinforcement Learning with Realizability and Single-policy Concentrability. COLT Wenhao Zhan, Baihe Huang, Audrey Huang, Nan Jiang, Jason D. Lee
2022	J	`jnl`	Offline Reinforcement Learning with Realizability and Single-policy Concentrability. CoRR Wenhao Zhan, Baihe Huang, Audrey Huang, Nan Jiang, Jason D. Lee
2022	A*	`conf`	On the Effective Number of Linear Regions in Shallow Univariate ReLU Networks: Convergence Guarantees and Implicit Bias. NeurIPS Itay Safran, Gal Vardi, Jason D. Lee
2022	J	`jnl`	On the Effective Number of Linear Regions in Shallow Univariate ReLU Networks: Convergence Guarantees and Implicit Bias. CoRR Itay Safran, Gal Vardi, Jason D. Lee
2022	A*	`conf`	Optimization-Based Separations for Neural Networks. COLT Itay Safran, Jason D. Lee
2022	J	`jnl`	PAC Reinforcement Learning for Predictive State Representations. CoRR Wenhao Zhan, Masatoshi Uehara, Wen Sun, Jason D. Lee
2022	A	`conf`	Provably Efficient Policy Optimization for Two-Player Zero-Sum Markov Games. AISTATS Yulai Zhao, Yuandong Tian, Jason D. Lee, Simon S. Du
2022	A*	`conf`	Provably Efficient Reinforcement Learning in Partially Observable Dynamical Systems. NeurIPS Masatoshi Uehara, Ayush Sekhari, Jason D. Lee, Nathan Kallus, Wen Sun
2022	J	`jnl`	Provably Efficient Reinforcement Learning in Partially Observable Dynamical Systems. CoRR Masatoshi Uehara, Ayush Sekhari, Jason D. Lee, Nathan Kallus, Wen Sun
2022	J	`jnl`	Reconstructing Training Data from Model Gradient, Provably. CoRR Zihan Wang, Jason D. Lee, Qi Lei
2022	J	`jnl`	Self-Stabilization: The Implicit Bias of Gradient Descent at the Edge of Stability. CoRR Alex Damian, Eshaan Nichani, Jason D. Lee
2022	A*	`conf`	Towards General Function Approximation in Zero-Sum Markov Games. ICLR Baihe Huang, Jason D. Lee, Zhaoran Wang, Zhuoran Yang
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`	A Theory of Label Propagation for Subpopulation Shift. ICML Tianle Cai, Ruiqi Gao, Jason D. Lee, Qi Lei
2021	J	`jnl`	A Theory of Label Propagation for Subpopulation Shift. CoRR Tianle Cai, Ruiqi Gao, Jason D. Lee, Qi Lei
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`	How Fine-Tuning Allows for Effective Meta-Learning. NeurIPS Kurtland Chua, Qi Lei, Jason D. Lee
2021	J	`jnl`	How Fine-Tuning Allows for Effective Meta-Learning. CoRR Kurtland Chua, Qi Lei, Jason D. Lee
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	A*	`conf`	Impact of Representation Learning in Linear Bandits. ICLR Jiaqi Yang, Wei Hu, Jason D. Lee, Simon Shaolei Du
2021	A*	`conf`	Label Noise SGD Provably Prefers Flat Global Minimizers. NeurIPS Alex Damian, Tengyu Ma, Jason D. Lee
2021	J	`jnl`	Label Noise SGD Provably Prefers Flat Global Minimizers. CoRR Alex Damian, Tengyu Ma, Jason D. Lee
2021	J	`jnl`	Linearized ADMM Converges to Second-Order Stationary Points for Non-Convex Problems. IEEE Trans. Signal Process. Songtao Lu, Jason D. Lee, Meisam Razaviyayn, Mingyi Hong
2021	J	`jnl`	MUSBO: Model-based Uncertainty Regularized and Sample Efficient Batch Optimization for Deployment Constrained Reinforcement Learning. CoRR DiJia Su, Jason D. Lee, John M. Mulvey, H. Vincent Poor
2021	A*	`conf`	Modeling from Features: a Mean-field Framework for Over-parameterized Deep Neural Networks. COLT Cong Fang, Jason D. Lee, Pengkun Yang, Tong Zhang
2021	A*	`conf`	Near-Optimal Linear Regression under Distribution Shift. ICML Qi Lei, Wei Hu, Jason D. Lee
2021	J	`jnl`	Near-Optimal Linear Regression under Distribution Shift. CoRR Qi Lei, Wei Hu, Jason D. Lee
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	J	`jnl`	Optimization-Based Separations for Neural Networks. CoRR Itay Safran, Jason D. Lee
2021	J	`jnl`	Policy Mirror Descent for Regularized Reinforcement Learning: A Generalized Framework with Linear Convergence. CoRR Wenhao Zhan, Shicong Cen, Baihe Huang, Yuxin Chen, Jason D. Lee, Yuejie Chi
2021	A*	`conf`	Predicting What You Already Know Helps: Provable Self-Supervised Learning. NeurIPS Jason D. Lee, Qi Lei, Nikunj Saunshi, Jiacheng Zhuo
2021	J	`jnl`	Provable Hierarchy-Based Meta-Reinforcement Learning. CoRR Kurtland Chua, Qi Lei, Jason D. Lee
2021	J	`jnl`	Provable Regret Bounds for Deep Online Learning and Control. CoRR Xinyi Chen, Edgar Minasyan, Jason D. Lee, Elad Hazan
2021	J	`jnl`	Provably Efficient Policy Gradient Methods for Two-Player Zero-Sum Markov Games. CoRR Yulai Zhao, Yuandong Tian, Jason D. Lee, Simon S. Du
2021	A*	`conf`	Shape Matters: Understanding the Implicit Bias of the Noise Covariance. COLT Jeff Z. HaoChen, Colin Wei, Jason D. Lee, Tengyu Ma
2021	J	`jnl`	Towards General Function Approximation in Zero-Sum Markov Games. CoRR Baihe Huang, Jason D. Lee, Zhaoran Wang, Zhuoran Yang
2020	A*	`conf`	Agnostic $Q$-learning with Function Approximation in Deterministic Systems: Near-Optimal Bounds on Approximation Error and Sample Complexity. NeurIPS Simon S. Du, Jason D. Lee, Gaurav Mahajan, Ruosong Wang
2020	J	`jnl`	Agnostic Q-learning with Function Approximation in Deterministic Systems: Tight Bounds on Approximation Error and Sample Complexity. CoRR Simon S. Du, Jason D. Lee, Gaurav Mahajan, Ruosong Wang
2020	A*	`conf`	Beyond Lazy Training for Over-parameterized Tensor Decomposition. NeurIPS Xiang Wang, Chenwei Wu, Jason D. Lee, Tengyu Ma, Rong Ge
2020	J	`jnl`	Beyond Lazy Training for Over-parameterized Tensor Decomposition. CoRR Xiang Wang, Chenwei Wu, Jason D. Lee, Tengyu Ma, Rong Ge
2020	A*	`conf`	Beyond Linearization: On Quadratic and Higher-Order Approximation of Wide Neural Networks. ICLR Yu Bai, Jason D. Lee
2020	A*	`conf`	Convergence of Meta-Learning with Task-Specific Adaptation over Partial Parameters. NeurIPS Kaiyi Ji, Jason D. Lee, Yingbin Liang, H. Vincent Poor
2020	J	`jnl`	Convergence of Meta-Learning with Task-Specific Adaptation over Partial Parameters. CoRR Kaiyi Ji, Jason D. Lee, Yingbin Liang, H. Vincent Poor
2020	J	`jnl`	Distributed Estimation for Principal Component Analysis: a Gap-free Approach. CoRR Xi Chen, Jason D. Lee, He Li, Yun Yang
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	A*	`conf`	Generalized Leverage Score Sampling for Neural Networks. NeurIPS Jason D. Lee, Ruoqi Shen, Zhao Song, Mengdi Wang, Zheng Yu
2020	J	`jnl`	Generalized Leverage Score Sampling for Neural Networks. CoRR Jason D. Lee, Ruoqi Shen, Zhao Song, Mengdi Wang, Zheng Yu
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`	How to Characterize The Landscape of Overparameterized Convolutional Neural Networks. NeurIPS Yihong Gu, Weizhong Zhang, Cong Fang, Jason D. Lee, Tong Zhang
2020	A*	`conf`	Implicit Bias in Deep Linear Classification: Initialization Scale vs Training Accuracy. NeurIPS Edward Moroshko, Blake E. Woodworth, Suriya Gunasekar, Jason D. Lee, Nati Srebro, Daniel Soudry
2020	J	`jnl`	Implicit Bias in Deep Linear Classification: Initialization Scale vs Training Accuracy. CoRR Edward Moroshko, Suriya Gunasekar, Blake E. Woodworth, Jason D. Lee, Nathan Srebro, Daniel Soudry
2020	A*	`conf`	Kernel and Rich Regimes in Overparametrized Models. COLT Blake E. Woodworth, Suriya Gunasekar, Jason D. Lee, Edward Moroshko, Pedro Savarese, Itay Golan, Daniel Soudry, Nathan Srebro
2020	J	`jnl`	Kernel and Rich Regimes in Overparametrized Models. CoRR Blake E. Woodworth, Suriya Gunasekar, Jason D. Lee, Edward Moroshko, Pedro Savarese, Itay Golan, Daniel Soudry, Nathan Srebro
2020	J	`jnl`	Modeling from Features: a Mean-field Framework for Over-parameterized Deep Neural Networks. CoRR Cong Fang, Jason D. Lee, Pengkun Yang, Tong Zhang
2020	A*	`conf`	Optimal transport mapping via input convex neural networks. ICML Ashok Vardhan Makkuva, Amirhossein Taghvaei, Sewoong Oh, Jason D. Lee
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`	Predicting What You Already Know Helps: Provable Self-Supervised Learning. CoRR Jason D. Lee, Qi Lei, Nikunj Saunshi, Jiacheng Zhuo
2020	J	`jnl`	Provable Benefits of Representation Learning in Linear Bandits. CoRR Jiaqi Yang, Wei Hu, Jason D. Lee, Simon S. Du
2020	A*	`conf`	SGD Learns One-Layer Networks in WGANs. ICML Qi Lei, Jason D. Lee, Alex Dimakis, Constantinos Daskalakis
2020	A*	`conf`	Sanity-Checking Pruning Methods: Random Tickets can Win the Jackpot. NeurIPS Jingtong Su, Yihang Chen, Tianle Cai, Tianhao Wu, Ruiqi Gao, Liwei Wang, Jason D. Lee
2020	J	`jnl`	Sanity-Checking Pruning Methods: Random Tickets can Win the Jackpot. CoRR Jingtong Su, Yihang Chen, Tianle Cai, Tianhao Wu, Ruiqi Gao, Liwei Wang, Jason D. Lee
2020	J	`jnl`	Shape Matters: Understanding the Implicit Bias of the Noise Covariance. CoRR Jeff Z. HaoChen, Colin Wei, Jason D. Lee, Tengyu Ma
2020	J	`jnl`	Steepest Descent Neural Architecture Optimization: Escaping Local Optimum with Signed Neural Splitting. CoRR Lemeng Wu, Mao Ye, Qi Lei, Jason D. Lee, Qiang Liu
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`	Towards Understanding Hierarchical Learning: Benefits of Neural Representations. NeurIPS Minshuo Chen, Yu Bai, Jason D. Lee, Tuo Zhao, Huan Wang, Caiming Xiong, Richard Socher
2020	J	`jnl`	Towards Understanding Hierarchical Learning: Benefits of Neural Representations. CoRR Minshuo Chen, Yu Bai, Jason D. Lee, Tuo Zhao, Huan Wang, Caiming Xiong, Richard Socher
2019	J	`jnl`	Beyond Linearization: On Quadratic and Higher-Order Approximation of Wide Neural Networks. CoRR Yu Bai, Jason D. Lee
2019	J	`jnl`	Convergence of Adversarial Training in Overparametrized Networks. CoRR Ruiqi Gao, Tianle Cai, Haochuan Li, Liwei Wang, Cho-Jui Hsieh, Jason D. Lee
2019	A*	`conf`	Convergence of Adversarial Training in Overparametrized Neural Networks. NeurIPS Ruiqi Gao, Tianle Cai, Haochuan Li, Cho-Jui Hsieh, Liwei Wang, Jason D. Lee
2019	A	`conf`	Convergence of Gradient Descent on Separable Data. AISTATS Mor Shpigel Nacson, Jason D. Lee, Suriya Gunasekar, Pedro Henrique Pamplona Savarese, Nathan Srebro, Daniel Soudry
2019	J	`jnl`	First-order methods almost always avoid strict saddle points. Math. Program. Jason D. Lee, Ioannis Panageas, Georgios Piliouras, Max Simchowitz, Michael I. Jordan, Benjamin Recht
2019	A*	`conf`	Gradient Descent Finds Global Minima of Deep Neural Networks. ICML Simon S. Du, Jason D. Lee, Haochuan Li, Liwei Wang, Xiyu Zhai
2019	J	`jnl`	Incremental Methods for Weakly Convex Optimization. CoRR Xiao Li, Zhihui Zhu, Anthony Man-Cho So, Jason D. Lee
2019	A*	`conf`	Lexicographic and Depth-Sensitive Margins in Homogeneous and Non-Homogeneous Deep Models. ICML Mor Shpigel Nacson, Suriya Gunasekar, Jason D. Lee, Nathan Srebro, Daniel Soudry
2019	J	`jnl`	Lexicographic and Depth-Sensitive Margins in Homogeneous and Non-Homogeneous Deep Models. CoRR Mor Shpigel Nacson, Suriya Gunasekar, Jason D. Lee, Nathan Srebro, Daniel Soudry
2019	A*	`conf`	Neural Temporal-Difference Learning Converges to Global Optima. NeurIPS Qi Cai, Zhuoran Yang, Jason D. Lee, Zhaoran Wang
2019	J	`jnl`	Neural Temporal-Difference Learning Converges to Global Optima. CoRR Qi Cai, Zhuoran Yang, Jason D. Lee, Zhaoran Wang
2019	J	`jnl`	Optimal transport mapping via input convex neural networks. CoRR Ashok Vardhan Makkuva, Amirhossein Taghvaei, Sewoong Oh, Jason D. Lee
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	A*	`conf`	Regularization Matters: Generalization and Optimization of Neural Nets v.s. their Induced Kernel. NeurIPS Colin Wei, Jason D. Lee, Qiang Liu, Tengyu Ma
2019	J	`jnl`	SGD Learns One-Layer Networks in WGANs. CoRR Qi Lei, Jason D. Lee, Alexandros G. Dimakis, Constantinos Daskalakis
2019	A*	`conf`	Solving a Class of Non-Convex Min-Max Games Using Iterative First Order Methods. NeurIPS Maher Nouiehed, Maziar Sanjabi, Tianjian Huang, Jason D. Lee, Meisam Razaviyayn
2019	J	`jnl`	Solving a Class of Non-Convex Min-Max Games Using Iterative First Order Methods. CoRR Maher Nouiehed, Maziar Sanjabi, Tianjian Huang, Jason D. Lee, Meisam Razaviyayn
2019	J	`jnl`	Theoretical Insights Into the Optimization Landscape of Over-Parameterized Shallow Neural Networks. IEEE Trans. Inf. Theory Mahdi Soltanolkotabi, Adel Javanmard, Jason D. Lee
2019	J	`jnl`	When Does Non-Orthogonal Tensor Decomposition Have No Spurious Local Minima? CoRR Maziar Sanjabi, Sina Baharlouei, Meisam Razaviyayn, Jason D. Lee
2018	A*	`conf`	Adding One Neuron Can Eliminate All Bad Local Minima. NeurIPS Shiyu Liang, Ruoyu Sun, Jason D. Lee, R. Srikant
2018	J	`jnl`	Adding One Neuron Can Eliminate All Bad Local Minima. CoRR Shiyu Liang, Ruoyu Sun, Jason D. Lee, R. Srikant
2018	A*	`conf`	Algorithmic Regularization in Learning Deep Homogeneous Models: Layers are Automatically Balanced. NeurIPS Simon S. Du, Wei Hu, Jason D. Lee
2018	J	`jnl`	Algorithmic Regularization in Learning Deep Homogeneous Models: Layers are Automatically Balanced. CoRR Simon S. Du, Wei Hu, Jason D. Lee
2018	A*	`conf`	Characterizing Implicit Bias in Terms of Optimization Geometry. ICML Suriya Gunasekar, Jason D. Lee, Daniel Soudry, Nathan Srebro
2018	J	`jnl`	Characterizing Implicit Bias in Terms of Optimization Geometry. CoRR Suriya Gunasekar, Jason D. Lee, Daniel Soudry, Nathan Srebro
2018	J	`jnl`	Convergence of Gradient Descent on Separable Data. CoRR Mor Shpigel Nacson, Jason D. Lee, Suriya Gunasekar, Nathan Srebro, Daniel Soudry
2018	J	`jnl`	Gradient Descent Finds Global Minima of Deep Neural Networks. CoRR Simon S. Du, Jason D. Lee, Haochuan Li, Liwei Wang, Xiyu Zhai
2018	A*	`conf`	Gradient Descent Learns One-hidden-layer CNN: Don't be Afraid of Spurious Local Minima. ICML Simon S. Du, Jason D. Lee, Yuandong Tian, Aarti Singh, Barnabás Póczos
2018	A*	`conf`	Gradient Primal-Dual Algorithm Converges to Second-Order Stationary Solution for Nonconvex Distributed Optimization Over Networks. ICML Mingyi Hong, Meisam Razaviyayn, Jason D. Lee
2018	J	`jnl`	Gradient Primal-Dual Algorithm Converges to Second-Order Stationary Solutions for Nonconvex Distributed Optimization. CoRR Mingyi Hong, Jason D. Lee, Meisam Razaviyayn
2018	A*	`conf`	Implicit Bias of Gradient Descent on Linear Convolutional Networks. NeurIPS Suriya Gunasekar, Jason D. Lee, Daniel Soudry, Nati Srebro
2018	J	`jnl`	Implicit Bias of Gradient Descent on Linear Convolutional Networks. CoRR Suriya Gunasekar, Jason D. Lee, Daniel Soudry, Nathan Srebro
2018	—	`conf`	Learning One-hidden-layer Neural Networks with Landscape Design. ICLR (Poster) Rong Ge, Jason D. Lee, Tengyu Ma
2018	—	`conf`	No Spurious Local Minima in a Two Hidden Unit ReLU Network. ICLR (Workshop) Chenwei Wu, Jiajun Luo, Jason D. Lee
2018	A*	`conf`	On the Convergence and Robustness of Training GANs with Regularized Optimal Transport. NeurIPS Maziar Sanjabi, Jimmy Ba, Meisam Razaviyayn, Jason D. Lee
2018	J	`jnl`	On the Margin Theory of Feedforward Neural Networks. CoRR Colin Wei, Jason D. Lee, Qiang Liu, Tengyu Ma
2018	A*	`conf`	On the Power of Over-parametrization in Neural Networks with Quadratic Activation. ICML Simon S. Du, Jason D. Lee
2018	J	`jnl`	On the Power of Over-parametrization in Neural Networks with Quadratic Activation. CoRR Simon S. Du, Jason D. Lee
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`	Solving Approximate Wasserstein GANs to Stationarity. CoRR Maziar Sanjabi, Jimmy Ba, Meisam Razaviyayn, Jason D. Lee
2018	J	`jnl`	Solving Non-Convex Non-Concave Min-Max Games Under Polyak-Łojasiewicz Condition. CoRR Maziar Sanjabi, Meisam Razaviyayn, Jason D. Lee
2018	J	`jnl`	Stochastic subgradient method converges on tame functions. CoRR Damek Davis, Dmitriy Drusvyatskiy, Sham M. Kakade, Jason D. Lee
2018	—	`conf`	When is a Convolutional Filter Easy to Learn? ICLR (Poster) Simon S. Du, Jason D. Lee, Yuandong Tian
2017	J	`jnl`	A Flexible Framework for Hypothesis Testing in High-dimensions. CoRR Adel Javanmard, Jason D. Lee
2017	J	`jnl`	An inexact subsampled proximal Newton-type method for large-scale machine learning. CoRR Xuanqing Liu, Cho-Jui Hsieh, Jason D. Lee, Yuekai Sun
2017	A	`conf`	Black-box Importance Sampling. AISTATS Qiang Liu, Jason D. Lee
2017	J	`jnl`	Communication-efficient Sparse Regression. J. Mach. Learn. Res. Jason D. Lee, Qiang Liu, Yuekai Sun, Jonathan E. Taylor
2017	J	`jnl`	Distributed Stochastic Variance Reduced Gradient Methods by Sampling Extra Data with Replacement. J. Mach. Learn. Res. Jason D. Lee, Qihang Lin, Tengyu Ma, Tianbao Yang
2017	J	`jnl`	First-order Methods Almost Always Avoid Saddle Points. CoRR Jason D. Lee, Ioannis Panageas, Georgios Piliouras, Max Simchowitz, Michael I. Jordan, Benjamin Recht
2017	—	`conf`	Gradient Descent Can Take Exponential Time to Escape Saddle Points. NIPS Simon S. Du, Chi Jin, Jason D. Lee, Michael I. Jordan, Aarti Singh, Barnabás Póczos
2017	J	`jnl`	Gradient Descent Can Take Exponential Time to Escape Saddle Points. CoRR Simon S. Du, Chi Jin, Jason D. Lee, Michael I. Jordan, Barnabás Póczos, Aarti Singh
2017	J	`jnl`	Gradient Descent Learns One-hidden-layer CNN: Don't be Afraid of Spurious Local Minima. CoRR Simon S. Du, Jason D. Lee, Yuandong Tian, Barnabás Póczos, Aarti Singh
2017	J	`jnl`	Learning One-hidden-layer Neural Networks with Landscape Design. CoRR Rong Ge, Jason D. Lee, Tengyu Ma
2017	A	`conf`	On the Learnability of Fully-Connected Neural Networks. AISTATS Yuchen Zhang, Jason D. Lee, Martin J. Wainwright, Michael I. Jordan
2017	A	`conf`	Sketching Meets Random Projection in the Dual: A Provable Recovery Algorithm for Big and High-dimensional Data. AISTATS Jialei Wang, Jason D. Lee, Mehrdad Mahdavi, Mladen Kolar, Nati Srebro
2017	J	`jnl`	Theoretical insights into the optimization landscape of over-parameterized shallow neural networks. CoRR Mahdi Soltanolkotabi, Adel Javanmard, Jason D. Lee
2017	J	`jnl`	When is a Convolutional Filter Easy To Learn? CoRR Simon S. Du, Jason D. Lee, Yuandong Tian
2016	A*	`conf`	A Kernelized Stein Discrepancy for Goodness-of-fit Tests. ICML Qiang Liu, Jason D. Lee, Michael I. Jordan
2016	J	`jnl`	Communication-efficient distributed statistical learning. CoRR Michael I. Jordan, Jason D. Lee, Yun Yang
2016	J	`jnl`	Gradient Descent Converges to Minimizers. CoRR Jason D. Lee, Max Simchowitz, Michael I. Jordan, Benjamin Recht
2016	A*	`conf`	Gradient Descent Only Converges to Minimizers. COLT Jason D. Lee, Max Simchowitz, Michael I. Jordan, Benjamin Recht
2016	A*	`conf`	L1-regularized Neural Networks are Improperly Learnable in Polynomial Time. ICML Yuchen Zhang, Jason D. Lee, Michael I. Jordan
2016	—	`conf`	Matrix Completion has No Spurious Local Minimum. NIPS Rong Ge, Jason D. Lee, Tengyu Ma
2016	J	`jnl`	Matrix Completion has No Spurious Local Minimum. CoRR Rong Ge, Jason D. Lee, Tengyu Ma
2016	J	`jnl`	Sketching Meets Random Projection in the Dual: A Provable Recovery Algorithm for Big and High-dimensional Data. CoRR Jialei Wang, Jason D. Lee, Mehrdad Mahdavi, Mladen Kolar, Nathan Srebro
2015	J	`jnl`	Communication-efficient sparse regression: a one-shot approach. CoRR Jason D. Lee, Yuekai Sun, Qiang Liu, Jonathan E. Taylor
2015	J	`jnl`	Distributed Stochastic Variance Reduced Gradient Methods. CoRR Jason D. Lee, Tengyu Ma, Qihang Lin
2015	—	`conf`	Evaluating the statistical significance of biclusters. NIPS Jason D. Lee, Yuekai Sun, Jonathan E. Taylor
2015	J	`jnl`	Learning Halfspaces and Neural Networks with Random Initialization. CoRR Yuchen Zhang, Jason D. Lee, Martin J. Wainwright, Michael I. Jordan
2015	J	`jnl`	Matrix completion and low-rank SVD via fast alternating least squares. J. Mach. Learn. Res. Trevor Hastie, Rahul Mazumder, Jason D. Lee, Reza Zadeh
2015	J	`jnl`	Selective Inference and Learning Mixed Graphical Models. CoRR Jason D. Lee
2015	J	`jnl`	ℓ CoRR Yuchen Zhang, Jason D. Lee, Michael I. Jordan
2014	—	`conf`	Exact Post Model Selection Inference for Marginal Screening. NIPS Jason D. Lee, Jonathan E. Taylor
2014	J	`jnl`	Exact Post Model Selection Inference for Marginal Screening. CoRR Jason D. Lee, Jonathan E. Taylor
2014	J	`jnl`	Proximal Newton-Type Methods for Minimizing Composite Functions. SIAM J. Optim. Jason D. Lee, Yuekai Sun, Michael A. Saunders
2014	—	`conf`	Scalable Methods for Nonnegative Matrix Factorizations of Near-separable Tall-and-skinny Matrices. NIPS Austin R. Benson, Jason D. Lee, Bartek Rajwa, David F. Gleich
2014	J	`jnl`	Scalable methods for nonnegative matrix factorizations of near-separable tall-and-skinny matrices. CoRR Austin R. Benson, Jason D. Lee, Bartek Rajwa, David F. Gleich
2013	—	`conf`	On model selection consistency of penalized M-estimators: a geometric theory. NIPS Jason D. Lee, Yuekai Sun, Jonathan E. Taylor
2013	J	`jnl`	On model selection consistency of regularized M-estimators. CoRR Jason D. Lee, Yuekai Sun, Jonathan E. Taylor
2013	A	`conf`	Structure Learning of Mixed Graphical Models. AISTATS Jason D. Lee, Trevor Hastie
2013	J	`jnl`	Using Multiple Samples to Learn Mixture Models. CoRR Jason D. Lee, Ran Gilad-Bachrach, Rich Caruana
2013	—	`conf`	Using multiple samples to learn mixture models. NIPS Jason D. Lee, Ran Gilad-Bachrach, Rich Caruana
2012	J	`jnl`	Learning Mixed Graphical Models CoRR Jason D. Lee, Trevor Hastie
2012	J	`jnl`	Proximal Newton-type Methods for Minimizing Convex Objective Functions in Composite Form CoRR Jason D. Lee, Yuekai Sun, Michael A. Saunders
2012	—	`conf`	Proximal Newton-type methods for convex optimization. NIPS Jason D. Lee, Yuekai Sun, Michael A. Saunders
2010	—	`conf`	Practical Large-Scale Optimization for Max-norm Regularization. NIPS Jason D. Lee, Ben Recht, Ruslan Salakhutdinov, Nathan Srebro, Joel A. Tropp
2009	C	`conf`	A distributed concurrent on-line test scheduling protocol for many-core NoC-based systems. ICCD Jason D. Lee, Rabi N. Mahapatra, Praveen Bhojwani
2008	—	`conf`	An On-Demand Test Triggering Mechanism for NoC-Based Safety-Critical Systems. ISQED Jason D. Lee, Nikhil Gupta, Praveen Bhojwani, Rabi N. Mahapatra
2008	C	`conf`	In-field NoC-based SoC testing with distributed test vector storage. ICCD Jason D. Lee, Rabi N. Mahapatra
2007	—	`conf`	A Safety Analysis Framework for COTS Microprocessors in Safety-Critical Applications. HASE Jason D. Lee, Praveen Bhojwani, Rabi N. Mahapatra
2007	A	`conf`	SAPP: scalable and adaptable peak power management in nocs. ISLPED Praveen Bhojwani, Jason D. Lee, Rabi N. Mahapatra