default search action
Jason D. Lee
Person information
- affiliation: Stanford University, Institute of Computational and Mathematical Engineering
Refine list
refinements active!
zoomed in on ?? of ?? records
view refined list in
export refined list as
showing all ?? records
2020 – today
- 2024
- [j11]Qi Cai
, Zhuoran Yang
Neural Temporal Difference and Q Learning Provably Converge to Global Optima. Math. Oper. Res. 49(1): 619-651 (2024) - [c114]Alex Damian, Loucas Pillaud-Vivien, Jason D. Lee, Joan Bruna:
Computational-Statistical Gaps in Gaussian Single-Index Models (Extended Abstract). COLT 2024: 1262 - [c113]Zihan Zhang, Yuxin Chen, Jason D. Lee, Simon S. Du:
Settling the sample complexity of online reinforcement learning. COLT 2024: 5213-5219 - [c112]Zihan Zhang, Wenhao Zhan, Yuxin Chen, Simon S. Du, Jason D. Lee:
Optimal Multi-Distribution Learning. COLT 2024: 5220-5223 - [c111]Yulai Zhao, Wenhao Zhan, Xiaoyan Hu, Ho-fung Leung, Farzan Farnia, Wen Sun, Jason D. Lee:
Provably Efficient CVaR RL in Low-rank MDPs. ICLR 2024 - [c110]Nayoung Lee, Kartik Sreenivasan, Jason D. Lee, Kangwook Lee, Dimitris Papailiopoulos:
Teaching Arithmetic to Small Transformers. ICLR 2024 - [c109]Kaifeng Lyu, Jikai Jin, Zhiyuan Li, Simon Shaolei Du, Jason D. Lee, Wei Hu:
Dichotomy of Early and Late Phase Implicit Biases Can Provably Induce Grokking. ICLR 2024 - [c108]Zihao Wang, Eshaan Nichani, Jason D. Lee:
Learning Hierarchical Polynomials with Three-Layer Neural Networks. ICLR 2024 - [c107]Wenhao Zhan, Masatoshi Uehara, Wen Sun, Jason D. Lee:
Provable Reward-Agnostic Preference-Based Reinforcement Learning. ICLR 2024 - [c106]Wenhao Zhan, Masatoshi Uehara, Nathan Kallus, Jason D. Lee, Wen Sun:
Provable Offline Preference-Based Reinforcement Learning. ICLR 2024 - [c105]Zihan Zhang, Jason D. Lee, Yuxin Chen, Simon Shaolei Du:
Horizon-Free Regret for Linear Markov Decision Processes. ICLR 2024 - [c104]Tianle Cai, Yuhong Li, Zhengyang Geng, Hongwu Peng, Jason D. Lee, Deming Chen, Tri Dao:
Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads. ICML 2024 - [c103]Uijeong Jang, Jason D. Lee, Ernest K. Ryu:
LoRA Training in the NTK Regime has No Spurious Local Minima. ICML 2024 - [c102]Hong Jun Jeon, Jason D. Lee, Qi Lei, Benjamin Van Roy:
An Information-Theoretic Analysis of In-Context Learning. ICML 2024 - [c101]Eshaan Nichani, Alex Damian, Jason D. Lee:
How Transformers Learn Causal Structure with Gradient Descent. ICML 2024 - [c100]Zixuan Wang, Stanley Wei, Daniel Hsu, Jason D. Lee:
Transformers Provably Learn Sparse Token Selection While Fully-Connected Nets Cannot. ICML 2024 - [c99]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:
Revisiting Zeroth-Order Optimization for Memory-Efficient LLM Fine-Tuning: A Benchmark. ICML 2024 - [c98]Zhenyu He, Zexuan Zhong, Tianle Cai, Jason D. Lee, Di He:
REST: Retrieval-Based Speculative Decoding. NAACL-HLT 2024: 1582-1595 - [i138]Tianle Cai, Yuhong Li, Zhengyang Geng, Hongwu Peng, Jason D. Lee, Deming Chen, Tri Dao:
Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads. CoRR abs/2401.10774 (2024) - [i137]Hong Jun Jeon, Jason D. Lee, Qi Lei, Benjamin Van Roy:
An Information-Theoretic Analysis of In-Context Learning. CoRR abs/2401.15530 (2024) - [i136]James Liu, Guangxuan Xiao, Kai Li, Jason D. Lee, Song Han, Tri Dao, Tianle Cai:
BitDelta: Your Fine-Tune May Only Be Worth One Bit. CoRR abs/2402.10193 (2024) - [i135]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:
Revisiting Zeroth-Order Optimization for Memory-Efficient LLM Fine-Tuning: A Benchmark. CoRR abs/2402.11592 (2024) - [i134]Uijeong Jang, Jason D. Lee, Ernest K. Ryu:
LoRA Training in the NTK Regime has No Spurious Local Minima. CoRR abs/2402.11867 (2024) - [i133]Eshaan Nichani, Alex Damian, Jason D. Lee:
How Transformers Learn Causal Structure with Gradient Descent. CoRR abs/2402.14735 (2024) - [i132]Angeliki Giannou, Liu Yang, Tianhao Wang, Dimitris Papailiopoulos, Jason D. Lee:
How Well Can Transformers Emulate In-context Newton's Method? CoRR abs/2403.03183 (2024) - [i131]Alex Damian, Loucas Pillaud-Vivien, Jason D. Lee, Joan Bruna:
Computational-Statistical Gaps in Gaussian Single-Index Models. CoRR abs/2403.05529 (2024) - [i130]Zihan Zhang, Jason D. Lee, Yuxin Chen, Simon S. Du:
Horizon-Free Regret for Linear Markov Decision Processes. CoRR abs/2403.10738 (2024) - [i129]Jonathan D. Chang, Wenhao Zhan, Owen Oertell, Kianté Brantley, Dipendra Misra, Jason D. Lee, Wen Sun:
Dataset Reset Policy Optimization for RLHF. CoRR abs/2404.08495 (2024) - [i128]Zhaolin Gao, Jonathan D. Chang, Wenhao Zhan, Owen Oertell, Gokul Swamy, Kianté Brantley, Thorsten Joachims, J. Andrew Bagnell, Jason D. Lee, Wen Sun:
REBEL: Reinforcement Learning via Regressing Relative Rewards. CoRR abs/2404.16767 (2024) - [i127]Jason D. Lee, Kazusato Oko, Taiji Suzuki, Denny Wu:
Neural network learns low-dimensional polynomials with SGD near the information-theoretic limit. CoRR abs/2406.01581 (2024) - [i126]Zixuan Wang, Stanley Wei, Daniel Hsu, Jason D. Lee:
Transformers Provably Learn Sparse Token Selection While Fully-Connected Nets Cannot. CoRR abs/2406.06893 (2024) - [i125]Licong Lin, Jingfeng Wu, Sham M. Kakade, Peter L. Bartlett, Jason D. Lee:
Scaling Laws in Linear Regression: Compute, Parameters, and Data. CoRR abs/2406.08466 (2024) - [i124]Qian Yu, Yining Wang, Baihe Huang, Qi Lei, Jason D. Lee:
Stochastic Zeroth-Order Optimization under Strongly Convexity and Lipschitz Hessian: Minimax Sample Complexity. CoRR abs/2406.19617 (2024) - [i123]Audrey Huang, Wenhao Zhan, Tengyang Xie, Jason D. Lee, Wen Sun, Akshay Krishnamurthy, Dylan J. Foster:
Correcting the Mythos of KL-Regularization: Direct Alignment without Overoptimization via Chi-Squared Preference Optimization. CoRR abs/2407.13399 (2024) - [i122]Wenhao Zhan, Scott Fujimoto, Zheqing Zhu, Jason D. Lee, Daniel R. Jiang, Yonathan Efroni:
Exploiting Structure in Offline Multi-Agent RL: The Benefits of Low Interaction Rank. CoRR abs/2410.01101 (2024) - [i121]Zhaolin Gao, Wenhao Zhan, Jonathan D. Chang, Gokul Swamy, Kianté Brantley, Jason D. Lee, Wen Sun:
Regressing the Relative Future: Efficient Policy Optimization for Multi-turn RLHF. CoRR abs/2410.04612 (2024) - [i120]Jaeyeon Kim, Sehyun Kwon, Joo Young Choi, Jongho Park, Jaewoong Cho, Jason D. Lee, Ernest K. Ryu:
Task Diversity Shortens the ICL Plateau. CoRR abs/2410.05448 (2024) - [i119]Yunwei Ren, Jason D. Lee:
Learning Orthogonal Multi-Index Models: A Fine-Grained Information Exponent Analysis. CoRR abs/2410.09678 (2024) - [i118]Yunwei Ren, Zixuan Wang, Jason D. Lee:
Learning and Transferring Sparse Contextual Bigrams with Linear Transformers. CoRR abs/2410.23438 (2024) - [i117]Jeremy Cohen, Alex Damian, Ameet Talwalkar, Zico Kolter, Jason D. Lee:
Understanding Optimization in Deep Learning with Central Flows. CoRR abs/2410.24206 (2024) - 2023
- [j10]Wenhao Zhan, Shicong Cen, Baihe Huang, Yuxin Chen
Policy Mirror Descent for Regularized Reinforcement Learning: A Generalized Framework with Linear Convergence. SIAM J. Optim. 33(2): 1061-1091 (2023) - [c97]Hanlin Zhu, Ruosong Wang, Jason D. Lee:
Provably Efficient Reinforcement Learning via Surprise Bound. AISTATS 2023: 4006-4032 - [c96]Qian Yu, Yining Wang, Baihe Huang, Qi Lei, Jason D. Lee:
Optimal Sample Complexity Bounds for Non-convex Optimization under Kurdyka-Lojasiewicz Condition. AISTATS 2023: 6806-6821 - [c95]Kurtland Chua, Qi Lei, Jason D. Lee:
Provable Hierarchy-Based Meta-Reinforcement Learning. AISTATS 2023: 10918-10967 - [c94]Alex Damian, Eshaan Nichani, Jason D. Lee:
Self-Stabilization: The Implicit Bias of Gradient Descent at the Edge of Stability. ICLR 2023 - [c93]Zhuoqing Song, Jason D. Lee, Zhuoran Yang:
Can We Find Nash Equilibria at a Linear Rate in Markov Games? ICLR 2023 - [c92]Wenhao Zhan, Jason D. Lee, Zhuoran Yang:
Decentralized Optimistic Hyperpolicy Mirror Descent: Provably No-Regret Learning in Markov Games. ICLR 2023 - [c91]Wenhao Zhan, Masatoshi Uehara, Wen Sun, Jason D. Lee:
PAC Reinforcement Learning for Predictive State Representations. ICLR 2023 - [c90]Hadi Daneshmand, Jason D. Lee, Chi Jin:
Efficient displacement convex optimization with particle gradient descent. ICML 2023: 6836-6854 - [c89]Angeliki Giannou, Shashank Rajput, Jy-yong Sohn, Kangwook Lee, Jason D. Lee, Dimitris Papailiopoulos:
Looped Transformers as Programmable Computers. ICML 2023: 11398-11442 - [c88]Jikai Jin, Zhiyuan Li
Understanding Incremental Learning of Gradient Descent: A Fine-grained Analysis of Matrix Sensing. ICML 2023: 15200-15238 - [c87]Masatoshi Uehara, Ayush Sekhari, Jason D. Lee, Nathan Kallus, Wen Sun:
Computationally Efficient PAC RL in POMDPs with Latent Determinism and Conditional Embeddings. ICML 2023: 34615-34641 - [c86]Yulai Zhao, Zhuoran Yang, Zhaoran Wang, Jason D. Lee:
Local Optimization Achieves Global Optimality in Multi-Agent Reinforcement Learning. ICML 2023: 42200-42226 - [c85]Xinyi Chen, Edgar Minasyan, Jason D. Lee, Elad Hazan:
Regret Guarantees for Online Deep Control. L4DC 2023: 1032-1045 - [c84]Gen Li, Wenhao Zhan, Jason D. Lee, Yuejie Chi, Yuxin Chen:
Reward-agnostic Fine-tuning: Provable Statistical Benefits of Hybrid Reinforcement Learning. NeurIPS 2023 - [c83]Alex Damian, Eshaan Nichani, Rong Ge, Jason D. Lee:
Smoothing the Landscape Boosts the Signal for SGD: Optimal Sample Complexity for Learning Single Index Models. NeurIPS 2023 - [c82]Sadhika Malladi, Tianyu Gao, Eshaan Nichani, Alex Damian, Jason D. Lee, Danqi Chen, Sanjeev Arora:
Fine-Tuning Language Models with Just Forward Passes. NeurIPS 2023 - [c81]Eshaan Nichani, Alex Damian, Jason D. Lee:
Provable Guarantees for Nonlinear Feature Learning in Three-Layer Neural Networks. NeurIPS 2023 - [c80]Masatoshi Uehara, Nathan Kallus, Jason D. Lee, Wen Sun:
Offline Minimax Soft-Q-learning Under Realizability and Partial Coverage. NeurIPS 2023 - [c79]Jingfeng Wu, Vladimir Braverman, Jason D. Lee:
Implicit Bias of Gradient Descent for Logistic Regression at the Edge of Stability. NeurIPS 2023 - [c78]Qian Yu, Yining Wang, Baihe Huang, Qi Lei, Jason D. Lee:
Sample Complexity for Quadratic Bandits: Hessian Dependent Bounds and Optimal Algorithms. NeurIPS 2023 - [i116]Jikai Jin, Zhiyuan Li, Kaifeng Lyu, Simon S. Du, Jason D. Lee:
Understanding Incremental Learning of Gradient Descent: A Fine-grained Analysis of Matrix Sensing. CoRR abs/2301.11500 (2023) - [i115]Angeliki Giannou, Shashank Rajput, Jy-yong Sohn, Kangwook Lee, Jason D. Lee, Dimitris S. Papailiopoulos:
Looped Transformers as Programmable Computers. CoRR abs/2301.13196 (2023) - [i114]Masatoshi Uehara, Nathan Kallus, Jason D. Lee, Wen Sun:
Refined Value-Based Offline RL under Realizability and Partial Coverage. CoRR abs/2302.02392 (2023) - [i113]Hadi Daneshmand, Jason D. Lee, Chi Jin:
Efficient displacement convex optimization with particle gradient descent. CoRR abs/2302.04753 (2023) - [i112]Hanlin Zhu, Ruosong Wang, Jason D. Lee:
Provably Efficient Reinforcement Learning via Surprise Bound. CoRR abs/2302.11634 (2023) - [i111]Zhuoqing Song, Jason D. Lee, Zhuoran Yang:
Can We Find Nash Equilibria at a Linear Rate in Markov Games? CoRR abs/2303.03095 (2023) - [i110]Yulai Zhao, Zhuoran Yang, Zhaoran Wang, Jason D. Lee:
Local Optimization Achieves Global Optimality in Multi-Agent Reinforcement Learning. CoRR abs/2305.04819 (2023) - [i109]Eshaan Nichani, Alex Damian, Jason D. Lee:
Provable Guarantees for Nonlinear Feature Learning in Three-Layer Neural Networks. CoRR abs/2305.06986 (2023) - [i108]Gen Li, Wenhao Zhan, Jason D. Lee, Yuejie Chi, Yuxin Chen:
Reward-agnostic Fine-tuning: Provable Statistical Benefits of Hybrid Reinforcement Learning. CoRR abs/2305.10282 (2023) - [i107]Alex Damian, Eshaan Nichani, Rong Ge, Jason D. Lee:
Smoothing the Landscape Boosts the Signal for SGD: Optimal Sample Complexity for Learning Single Index Models. CoRR abs/2305.10633 (2023) - [i106]Jingfeng Wu, Vladimir Braverman, Jason D. Lee:
Implicit Bias of Gradient Descent for Logistic Regression at the Edge of Stability. CoRR abs/2305.11788 (2023) - [i105]Wenhao Zhan, Masatoshi Uehara, Nathan Kallus, Jason D. Lee, Wen Sun:
Provable Offline Reinforcement Learning with Human Feedback. CoRR abs/2305.14816 (2023) - [i104]Sadhika Malladi, Tianyu Gao, Eshaan Nichani, Alex Damian, Jason D. Lee, Danqi Chen, Sanjeev Arora:
Fine-Tuning Language Models with Just Forward Passes. CoRR abs/2305.17333 (2023) - [i103]Ziang Song, Tianle Cai, Jason D. Lee, Weijie J. Su:
Reward Collapse in Aligning Large Language Models. CoRR abs/2305.17608 (2023) - [i102]Wenhao Zhan, Masatoshi Uehara, Wen Sun, Jason D. Lee:
How to Query Human Feedback Efficiently in RL? CoRR abs/2305.18505 (2023) - [i101]Etash Kumar Guha, Jason D. Lee:
Solving Robust MDPs through No-Regret Dynamics. CoRR abs/2305.19035 (2023) - [i100]Qian Yu, Yining Wang, Baihe Huang, Qi Lei, Jason D. Lee:
Sample Complexity for Quadratic Bandits: Hessian Dependent Bounds and Optimal Algorithms. CoRR abs/2306.12383 (2023) - [i99]Tianle Cai, Kaixuan Huang, Jason D. Lee, Mengdi Wang:
Scaling In-Context Demonstrations with Structured Attention. CoRR abs/2307.02690 (2023) - [i98]Nayoung Lee, Kartik Sreenivasan, Jason D. Lee, Kangwook Lee, Dimitris Papailiopoulos:
Teaching Arithmetic to Small Transformers. CoRR abs/2307.03381 (2023) - [i97]Zihan Zhang, Yuxin Chen, Jason D. Lee, Simon S. Du:
Settling the Sample Complexity of Online Reinforcement Learning. CoRR abs/2307.13586 (2023) - [i96]Zhenyu He, Zexuan Zhong, Tianle Cai, Jason D. Lee, Di He:
REST: Retrieval-Based Speculative Decoding. CoRR abs/2311.08252 (2023) - [i95]Yulai Zhao, Wenhao Zhan, Xiaoyan Hu
Provably Efficient CVaR RL in Low-rank MDPs. CoRR abs/2311.11965 (2023) - [i94]Zihao Wang, Eshaan Nichani, Jason D. Lee:
Learning Hierarchical Polynomials with Three-Layer Neural Networks. CoRR abs/2311.13774 (2023) - [i93]Kaifeng Lyu, Jikai Jin, Zhiyuan Li
Dichotomy of Early and Late Phase Implicit Biases Can Provably Induce Grokking. CoRR abs/2311.18817 (2023) - [i92]Zihan Zhang, Wenhao Zhan, Yuxin Chen, Simon S. Du, Jason D. Lee:
Optimal Multi-Distribution Learning. CoRR abs/2312.05134 (2023) - [i91]Baihe Huang, Banghua Zhu, Hanlin Zhu, Jason D. Lee, Jiantao Jiao, Michael I. Jordan:
Towards Optimal Statistical Watermarking. CoRR abs/2312.07930 (2023) - 2022
- [c77]Yulai Zhao, Yuandong Tian, Jason D. Lee, Simon S. Du:
Provably Efficient Policy Optimization for Two-Player Zero-Sum Markov Games. AISTATS 2022: 2736-2761 - [c76]Itay Safran, Jason D. Lee:
Optimization-Based Separations for Neural Networks. COLT 2022: 3-64 - [c75]Wenhao Zhan, Baihe Huang, Audrey Huang, Nan Jiang, Jason D. Lee:
Offline Reinforcement Learning with Realizability and Single-policy Concentrability. COLT 2022: 2730-2775 - [c74]Alexandru Damian, Jason D. Lee, Mahdi Soltanolkotabi
Neural Networks can Learn Representations with Gradient Descent. COLT 2022: 5413-5452 - [c73]DiJia Su, Jason D. Lee, John M. Mulvey, H. Vincent Poor:
Competitive Multi-Agent Reinforcement Learning with Self-Supervised Representation. ICASSP 2022: 4098-4102 - [c72]Baihe Huang, Jason D. Lee, Zhaoran Wang, Zhuoran Yang:
Towards General Function Approximation in Zero-Sum Markov Games. ICLR 2022 - [c71]Zhiyuan Li, Tianhao Wang, Jason D. Lee, Sanjeev Arora:
Implicit Bias of Gradient Descent on Reparametrized Models: On Equivalence to Mirror Descent. NeurIPS 2022 - [c70]Eshaan Nichani, Yu Bai, Jason D. Lee:
Identifying good directions to escape the NTK regime and efficiently learn low-degree plus sparse polynomials. NeurIPS 2022 - [c69]Christopher De Sa, Satyen Kale, Jason D. Lee, Ayush Sekhari, Karthik Sridharan:
From Gradient Flow on Population Loss to Learning with Stochastic Gradient Descent. NeurIPS 2022 - [c68]Itay Safran, Gal Vardi, Jason D. Lee:
On the Effective Number of Linear Regions in Shallow Univariate ReLU Networks: Convergence Guarantees and Implicit Bias. NeurIPS 2022 - [c67]Masatoshi Uehara, Ayush Sekhari, Jason D. Lee, Nathan Kallus, Wen Sun:
Provably Efficient Reinforcement Learning in Partially Observable Dynamical Systems. NeurIPS 2022 - [i90]Wenhao Zhan, Baihe Huang, Audrey Huang, Nan Jiang, Jason D. Lee:
Offline Reinforcement Learning with Realizability and Single-policy Concentrability. CoRR abs/2202.04634 (2022) - [i89]Jiaqi Yang, Qi Lei, Jason D. Lee, Simon S. Du:
Nearly Minimax Algorithms for Linear Bandits with Shared Representation. CoRR abs/2203.15664 (2022) - [i88]Itay Safran, Gal Vardi, Jason D. Lee:
On the Effective Number of Linear Regions in Shallow Univariate ReLU Networks: Convergence Guarantees and Implicit Bias. CoRR abs/2205.09072 (2022) - [i87]Wenhao Zhan, Jason D. Lee, Zhuoran Yang:
Decentralized Optimistic Hyperpolicy Mirror Descent: Provably No-Regret Learning in Markov Games. CoRR abs/2206.01588 (2022) - [i86]Eshaan Nichani, Yu Bai, Jason D. Lee:
Identifying good directions to escape the NTK regime and efficiently learn low-degree plus sparse polynomials. CoRR abs/2206.03688 (2022) - [i85]Masatoshi Uehara, Ayush Sekhari, Jason D. Lee, Nathan Kallus, Wen Sun:
Provably Efficient Reinforcement Learning in Partially Observable Dynamical Systems. CoRR abs/2206.12020 (2022) - [i84]Masatoshi Uehara, Ayush Sekhari, Jason D. Lee, Nathan Kallus, Wen Sun:
Computationally Efficient PAC RL in POMDPs with Latent Determinism and Conditional Embeddings. CoRR abs/2206.12081 (2022) - [i83]Alex Damian, Jason D. Lee, Mahdi Soltanolkotabi
Neural Networks can Learn Representations with Gradient Descent. CoRR abs/2206.15144 (2022) - [i82]Zhiyuan Li, Tianhao Wang, Jason D. Lee, Sanjeev Arora:
Implicit Bias of Gradient Descent on Reparametrized Models: On Equivalence to Mirror Descent. CoRR abs/2207.04036 (2022) - [i81]Wenhao Zhan, Masatoshi Uehara, Wen Sun, Jason D. Lee:
PAC Reinforcement Learning for Predictive State Representations. CoRR abs/2207.05738 (2022) - [i80]Alex Damian, Eshaan Nichani, Jason D. Lee:
Self-Stabilization: The Implicit Bias of Gradient Descent at the Edge of Stability. CoRR abs/2209.15594 (2022) - [i79]Satyen Kale, Jason D. Lee, Chris De Sa, Ayush Sekhari, Karthik Sridharan:
From Gradient Flow on Population Loss to Learning with Stochastic Gradient Descent. CoRR abs/2210.06705 (2022) - [i78]Zihan Wang, Jason D. Lee, Qi Lei:
Reconstructing Training Data from Model Gradient, Provably. CoRR abs/2212.03714 (2022) - 2021
- [j9]Alekh Agarwal, Sham M. Kakade, Jason D. Lee, Gaurav Mahajan:
On the Theory of Policy Gradient Methods: Optimality, Approximation, and Distribution Shift. J. Mach. Learn. Res. 22: 98:1-98:76 (2021) - [j8]Songtao Lu
Linearized ADMM Converges to Second-Order Stationary Points for Non-Convex Problems. IEEE Trans. Signal Process. 69: 4859-4874 (2021) - [c66]Cong Fang, Jason D. Lee, Pengkun Yang, Tong Zhang:
Modeling from Features: a Mean-field Framework for Over-parameterized Deep Neural Networks. COLT 2021: 1887-1936 - [c65]Jeff Z. HaoChen, Colin Wei, Jason D. Lee, Tengyu Ma:
Shape Matters: Understanding the Implicit Bias of the Noise Covariance. COLT 2021: 2315-2357 - [c64]Simon Shaolei Du, Wei Hu, Sham M. Kakade, Jason D. Lee, Qi Lei:
Few-Shot Learning via Learning the Representation, Provably. ICLR 2021 - [c63]Jiaqi Yang, Wei Hu, Jason D. Lee, Simon Shaolei Du:
Impact of Representation Learning in Linear Bandits. ICLR 2021 - [c62]Yu Bai, Minshuo Chen, Pan Zhou, Tuo Zhao, Jason D. Lee, Sham M. Kakade, Huan Wang, Caiming Xiong:
How Important is the Train-Validation Split in Meta-Learning? ICML 2021: 543-553 - [c61]Tianle Cai, Ruiqi Gao, Jason D. Lee, Qi Lei:
A Theory of Label Propagation for Subpopulation Shift. ICML 2021: 1170-1182 - [c60]Simon S. Du, Sham M. Kakade, Jason D. Lee, Shachar Lovett, Gaurav Mahajan, Wen Sun, Ruosong Wang:
Bilinear Classes: A Structural Framework for Provable Generalization in RL. ICML 2021: 2826-2836 - [c59]Qi Lei, Wei Hu, Jason D. Lee:
Near-Optimal Linear Regression under Distribution Shift. ICML 2021: 6164-6174 - [c58]Jason D. Lee, Qi Lei, Nikunj Saunshi, Jiacheng Zhuo:
Predicting What You Already Know Helps: Provable Self-Supervised Learning. NeurIPS 2021: 309-323 - [c57]Kurtland Chua, Qi Lei, Jason D. Lee:
How Fine-Tuning Allows for Effective Meta-Learning. NeurIPS 2021: 8871-8884 - [c56]Baihe Huang, Kaixuan Huang, Sham M. Kakade, Jason D. Lee, Qi Lei, Runzhe Wang, Jiaqi Yang:
Going Beyond Linear RL: Sample Efficient Neural Function Approximation. NeurIPS 2021: 8968-8983 - [c55]Alex Damian, Tengyu Ma, Jason D. Lee:
Label Noise SGD Provably Prefers Flat Global Minimizers. NeurIPS 2021: 27449-27461 - [c54]Baihe Huang, Kaixuan Huang, Sham M. Kakade, Jason D. Lee, Qi Lei, Runzhe Wang, Jiaqi Yang:
Optimal Gradient-based Algorithms for Non-concave Bandit Optimization. NeurIPS 2021: 29101-29115 - [i77]Yulai Zhao, Yuandong Tian, Jason D. Lee, Simon S. Du:
Provably Efficient Policy Gradient Methods for Two-Player Zero-Sum Markov Games. CoRR abs/2102.08903 (2021) - [i76]Tianle Cai, Ruiqi Gao, Jason D. Lee, Qi Lei:
A Theory of Label Propagation for Subpopulation Shift. CoRR abs/2102.11203 (2021) - [i75]DiJia Su, Jason D. Lee, John M. Mulvey, H. Vincent Poor:
MUSBO: Model-based Uncertainty Regularized and Sample Efficient Batch Optimization for Deployment Constrained Reinforcement Learning. CoRR abs/2102.11448 (2021) - [i74]Simon S. Du, Sham M. Kakade, Jason D. Lee, Shachar Lovett, Gaurav Mahajan, Wen Sun, Ruosong Wang:
Bilinear Classes: A Structural Framework for Provable Generalization in RL. CoRR abs/2103.10897 (2021) - [i73]Kurtland Chua, Qi Lei, Jason D. Lee:
How Fine-Tuning Allows for Effective Meta-Learning. CoRR abs/2105.02221 (2021) - [i72]Wenhao Zhan, Shicong Cen, Baihe Huang, Yuxin Chen, Jason D. Lee, Yuejie Chi:
Policy Mirror Descent for Regularized Reinforcement Learning: A Generalized Framework with Linear Convergence. CoRR abs/2105.11066 (2021) - [i71]Alex Damian, Tengyu Ma, Jason D. Lee:
Label Noise SGD Provably Prefers Flat Global Minimizers. CoRR abs/2106.06530 (2021) - [i70]Qi Lei, Wei Hu, Jason D. Lee:
Near-Optimal Linear Regression under Distribution Shift. CoRR abs/2106.12108 (2021) - [i69]Kaixuan Huang, Sham M. Kakade, Jason D. Lee, Qi Lei:
A Short Note on the Relationship of Information Gain and Eluder Dimension. CoRR abs/2107.02377 (2021) - [i68]Baihe Huang, Kaixuan Huang, Sham M. Kakade, Jason D. Lee, Qi Lei, Runzhe Wang, Jiaqi Yang:
Optimal Gradient-based Algorithms for Non-concave Bandit Optimization. CoRR abs/2107.04518 (2021) - [i67]Baihe Huang, Kaixuan Huang, Sham M. Kakade, Jason D. Lee, Qi Lei, Runzhe Wang, Jiaqi Yang:
Going Beyond Linear RL: Sample Efficient Neural Function Approximation. CoRR abs/2107.06466 (2021) - [i66]Baihe Huang, Jason D. Lee, Zhaoran Wang, Zhuoran Yang:
Towards General Function Approximation in Zero-Sum Markov Games. CoRR abs/2107.14702 (2021) - [i65]Xinyi Chen, Edgar Minasyan, Jason D. Lee, Elad Hazan:
Provable Regret Bounds for Deep Online Learning and Control. CoRR abs/2110.07807 (2021) - [i64]Kurtland Chua, Qi Lei, Jason D. Lee:
Provable Hierarchy-Based Meta-Reinforcement Learning. CoRR abs/2110.09507 (2021) - [i63]Itay Safran, Jason D. Lee:
Optimization-Based Separations for Neural Networks. CoRR abs/2112.02393 (2021) - 2020
- [j7]Damek Davis, Dmitriy Drusvyatskiy, Sham M. Kakade, Jason D. Lee:
Stochastic Subgradient Method Converges on Tame Functions. Found. Comput. Math. 20(1): 119-154 (2020) - [c53]Alekh Agarwal, Sham M. Kakade, Jason D. Lee, Gaurav Mahajan:
Optimality and Approximation with Policy Gradient Methods in Markov Decision Processes. COLT 2020: 64-66 - [c52]Blake E. Woodworth, Suriya Gunasekar, Jason D. Lee, Edward Moroshko, Pedro Savarese, Itay Golan, Daniel Soudry, Nathan Srebro:
Kernel and Rich Regimes in Overparametrized Models. COLT 2020: 3635-3673 - [c51]Yu Bai, Jason D. Lee:
Beyond Linearization: On Quadratic and Higher-Order Approximation of Wide Neural Networks. ICLR 2020 - [c50]Qi Lei, Jason D. Lee, Alex Dimakis, Constantinos Daskalakis:
SGD Learns One-Layer Networks in WGANs. ICML 2020: 5799-5808 - [c49]Ashok Vardhan Makkuva, Amirhossein Taghvaei, Sewoong Oh, Jason D. Lee:
Optimal transport mapping via input convex neural networks. ICML 2020: 6672-6681 - [c48]Minshuo Chen, Yu Bai, Jason D. Lee, Tuo Zhao, Huan Wang, Caiming Xiong, Richard Socher:
Towards Understanding Hierarchical Learning: Benefits of Neural Representations. NeurIPS 2020 - [c47]Simon S. Du, Jason D. Lee, Gaurav Mahajan, Ruosong Wang:
Agnostic $Q$-learning with Function Approximation in Deterministic Systems: Near-Optimal Bounds on Approximation Error and Sample Complexity. NeurIPS 2020 - [c46]Yihong Gu, Weizhong Zhang, Cong Fang, Jason D. Lee, Tong Zhang:
How to Characterize The Landscape of Overparameterized Convolutional Neural Networks. NeurIPS 2020 - [c45]Kaiyi Ji, Jason D. Lee, Yingbin Liang, H. Vincent Poor:
Convergence of Meta-Learning with Task-Specific Adaptation over Partial Parameters. NeurIPS 2020 - [c44]Jason D. Lee, Ruoqi Shen, Zhao Song, Mengdi Wang, Zheng Yu:
Generalized Leverage Score Sampling for Neural Networks. NeurIPS 2020 - [c43]Edward Moroshko, Blake E. Woodworth, Suriya Gunasekar, Jason D. Lee, Nati Srebro, Daniel Soudry:
Implicit Bias in Deep Linear Classification: Initialization Scale vs Training Accuracy. NeurIPS 2020 - [c42]Jingtong Su, Yihang Chen, Tianle Cai, Tianhao Wu, Ruiqi Gao, Liwei Wang, Jason D. Lee:
Sanity-Checking Pruning Methods: Random Tickets can Win the Jackpot. NeurIPS 2020 - [c41]Xiang Wang, Chenwei Wu, Jason D. Lee, Tengyu Ma, Rong Ge:
Beyond Lazy Training for Over-parameterized Tensor Decomposition. NeurIPS 2020 - [i62]Simon S. Du, Jason D. Lee, Gaurav Mahajan, Ruosong Wang:
Agnostic Q-learning with Function Approximation in Deterministic Systems: Tight Bounds on Approximation Error and Sample Complexity. CoRR abs/2002.07125 (2020) - [i61]Blake E. Woodworth, Suriya Gunasekar, Jason D. Lee, Edward Moroshko, Pedro Savarese, Itay Golan, Daniel Soudry, Nathan Srebro:
Kernel and Rich Regimes in Overparametrized Models. CoRR abs/2002.09277 (2020) - [i60]Simon S. Du, Wei Hu, Sham M. Kakade, Jason D. Lee, Qi Lei:
Few-Shot Learning via Learning the Representation, Provably. CoRR abs/2002.09434 (2020) - [i59]Lemeng Wu, Mao Ye, Qi Lei, Jason D. Lee, Qiang Liu:
Steepest Descent Neural Architecture Optimization: Escaping Local Optimum with Signed Neural Splitting. CoRR abs/2003.10392 (2020) - [i58]Xi Chen, Jason D. Lee, He Li, Yun Yang:
Distributed Estimation for Principal Component Analysis: a Gap-free Approach. CoRR abs/2004.02336 (2020) - [i57]Jeff Z. HaoChen, Colin Wei, Jason D. Lee, Tengyu Ma:
Shape Matters: Understanding the Implicit Bias of the Noise Covariance. CoRR abs/2006.08680 (2020) - [i56]Kaiyi Ji, Jason D. Lee, Yingbin Liang, H. Vincent Poor:
Convergence of Meta-Learning with Task-Specific Adaptation over Partial Parameters. CoRR abs/2006.09486 (2020) - [i55]Minshuo Chen, Yu Bai, Jason D. Lee, Tuo Zhao, Huan Wang, Caiming Xiong, Richard Socher:
Towards Understanding Hierarchical Learning: Benefits of Neural Representations. CoRR abs/2006.13436 (2020) - [i54]Cong Fang, Jason D. Lee, Pengkun Yang, Tong Zhang:
Modeling from Features: a Mean-field Framework for Over-parameterized Deep Neural Networks. CoRR abs/2007.01452 (2020) - [i53]Edward Moroshko, Suriya Gunasekar, Blake E. Woodworth, Jason D. Lee, Nathan Srebro, Daniel Soudry:
Implicit Bias in Deep Linear Classification: Initialization Scale vs Training Accuracy. CoRR abs/2007.06738 (2020) - [i52]Jason D. Lee, Qi Lei, Nikunj Saunshi, Jiacheng Zhuo:
Predicting What You Already Know Helps: Provable Self-Supervised Learning. CoRR abs/2008.01064 (2020) - [i51]Jason D. Lee, Ruoqi Shen, Zhao Song, Mengdi Wang, Zheng Yu:
Generalized Leverage Score Sampling for Neural Networks. CoRR abs/2009.09829 (2020) - [i50]Jingtong Su, Yihang Chen, Tianle Cai, Tianhao Wu, Ruiqi Gao, Liwei Wang, Jason D. Lee:
Sanity-Checking Pruning Methods: Random Tickets can Win the Jackpot. CoRR abs/2009.11094 (2020) - [i49]Yu Bai, Minshuo Chen, Pan Zhou, Tuo Zhao, Jason D. Lee, Sham M. Kakade, Huan Wang, Caiming Xiong:
How Important is the Train-Validation Split in Meta-Learning? CoRR abs/2010.05843 (2020) - [i48]Jiaqi Yang, Wei Hu, Jason D. Lee, Simon S. Du:
Provable Benefits of Representation Learning in Linear Bandits. CoRR abs/2010.06531 (2020) - [i47]Xiang Wang, Chenwei Wu, Jason D. Lee, Tengyu Ma, Rong Ge:
Beyond Lazy Training for Over-parameterized Tensor Decomposition. CoRR abs/2010.11356 (2020)
2010 – 2019
- 2019
- [j6]Jason D. Lee
First-order methods almost always avoid strict saddle points. Math. Program. 176(1-2): 311-337 (2019) - [j5]Mahdi Soltanolkotabi
Theoretical Insights Into the Optimization Landscape of Over-Parameterized Shallow Neural Networks. IEEE Trans. Inf. Theory 65(2): 742-769 (2019) - [c40]Mor Shpigel Nacson, Jason D. Lee, Suriya Gunasekar, Pedro Henrique Pamplona Savarese, Nathan Srebro, Daniel Soudry:
Convergence of Gradient Descent on Separable Data. AISTATS 2019: 3420-3428 - [c39]Simon S. Du, Jason D. Lee, Haochuan Li, Liwei Wang, Xiyu Zhai:
Gradient Descent Finds Global Minima of Deep Neural Networks. ICML 2019: 1675-1685 - [c38]Mor Shpigel Nacson, Suriya Gunasekar, Jason D. Lee, Nathan Srebro, Daniel Soudry:
Lexicographic and Depth-Sensitive Margins in Homogeneous and Non-Homogeneous Deep Models. ICML 2019: 4683-4692 - [c37]Colin Wei, Jason D. Lee, Qiang Liu, Tengyu Ma:
Regularization Matters: Generalization and Optimization of Neural Nets v.s. their Induced Kernel. NeurIPS 2019: 9709-9721 - [c36]Qi Cai, Zhuoran Yang, Jason D. Lee, Zhaoran Wang:
Neural Temporal-Difference Learning Converges to Global Optima. NeurIPS 2019: 11312-11322 - [c35]Ruiqi Gao, Tianle Cai, Haochuan Li, Cho-Jui Hsieh, Liwei Wang, Jason D. Lee:
Convergence of Adversarial Training in Overparametrized Neural Networks. NeurIPS 2019: 13009-13020 - [c34]Maher Nouiehed, Maziar Sanjabi, Tianjian Huang, Jason D. Lee, Meisam Razaviyayn:
Solving a Class of Non-Convex Min-Max Games Using Iterative First Order Methods. NeurIPS 2019: 14905-14916 - [i46]Maher Nouiehed, Maziar Sanjabi, Tianjian Huang, Jason D. Lee, Meisam Razaviyayn:
Solving a Class of Non-Convex Min-Max Games Using Iterative First Order Methods. CoRR abs/1902.08297 (2019) - [i45]Mor Shpigel Nacson, Suriya Gunasekar, Jason D. Lee, Nathan Srebro, Daniel Soudry:
Lexicographic and Depth-Sensitive Margins in Homogeneous and Non-Homogeneous Deep Models. CoRR abs/1905.07325 (2019) - [i44]Qi Cai, Zhuoran Yang, Jason D. Lee, Zhaoran Wang:
Neural Temporal-Difference Learning Converges to Global Optima. CoRR abs/1905.10027 (2019) - [i43]Ruiqi Gao, Tianle Cai, Haochuan Li, Liwei Wang, Cho-Jui Hsieh, Jason D. Lee:
Convergence of Adversarial Training in Overparametrized Networks. CoRR abs/1906.07916 (2019) - [i42]Xiao Li, Zhihui Zhu, Anthony Man-Cho So, Jason D. Lee:
Incremental Methods for Weakly Convex Optimization. CoRR abs/1907.11687 (2019) - [i41]Alekh Agarwal, Sham M. Kakade, Jason D. Lee, Gaurav Mahajan:
Optimality and Approximation with Policy Gradient Methods in Markov Decision Processes. CoRR abs/1908.00261 (2019) - [i40]Ashok Vardhan Makkuva, Amirhossein Taghvaei, Sewoong Oh, Jason D. Lee:
Optimal transport mapping via input convex neural networks. CoRR abs/1908.10962 (2019) - [i39]Yu Bai, Jason D. Lee:
Beyond Linearization: On Quadratic and Higher-Order Approximation of Wide Neural Networks. CoRR abs/1910.01619 (2019) - [i38]Qi Lei, Jason D. Lee, Alexandros G. Dimakis, Constantinos Daskalakis:
SGD Learns One-Layer Networks in WGANs. CoRR abs/1910.07030 (2019) - [i37]Maziar Sanjabi, Sina Baharlouei, Meisam Razaviyayn, Jason D. Lee:
When Does Non-Orthogonal Tensor Decomposition Have No Spurious Local Minima? CoRR abs/1911.09815 (2019) - 2018
- [c33]Rong Ge, Jason D. Lee, Tengyu Ma:
Learning One-hidden-layer Neural Networks with Landscape Design. ICLR (Poster) 2018 - [c32]Simon S. Du, Jason D. Lee, Yuandong Tian:
When is a Convolutional Filter Easy to Learn? ICLR (Poster) 2018 - [c31]Chenwei Wu, Jiajun Luo, Jason D. Lee:
No Spurious Local Minima in a Two Hidden Unit ReLU Network. ICLR (Workshop) 2018 - [c30]Simon S. Du, Jason D. Lee:
On the Power of Over-parametrization in Neural Networks with Quadratic Activation. ICML 2018: 1328-1337 - [c29]Simon S. Du, Jason D. Lee, Yuandong Tian, Aarti Singh, Barnabás Póczos:
Gradient Descent Learns One-hidden-layer CNN: Don't be Afraid of Spurious Local Minima. ICML 2018: 1338-1347 - [c28]Suriya Gunasekar, Jason D. Lee, Daniel Soudry, Nathan Srebro:
Characterizing Implicit Bias in Terms of Optimization Geometry. ICML 2018: 1827-1836 - [c27]Mingyi Hong, Meisam Razaviyayn, Jason D. Lee:
Gradient Primal-Dual Algorithm Converges to Second-Order Stationary Solution for Nonconvex Distributed Optimization Over Networks. ICML 2018: 2014-2023 - [c26]Simon S. Du, Wei Hu, Jason D. Lee:
Algorithmic Regularization in Learning Deep Homogeneous Models: Layers are Automatically Balanced. NeurIPS 2018: 382-393 - [c25]Shiyu Liang, Ruoyu Sun, Jason D. Lee, R. Srikant:
Adding One Neuron Can Eliminate All Bad Local Minima. NeurIPS 2018: 4355-4365 - [c24]Maziar Sanjabi, Jimmy Ba, Meisam Razaviyayn, Jason D. Lee:
On the Convergence and Robustness of Training GANs with Regularized Optimal Transport. NeurIPS 2018: 7091-7101 - [c23]Sham M. Kakade, Jason D. Lee:
Provably Correct Automatic Sub-Differentiation for Qualified Programs. NeurIPS 2018: 7125-7135 - [c22]Suriya Gunasekar, Jason D. Lee, Daniel Soudry, Nati Srebro:
Implicit Bias of Gradient Descent on Linear Convolutional Networks. NeurIPS 2018: 9482-9491 - [i36]Suriya Gunasekar, Jason D. Lee, Daniel Soudry, Nathan Srebro:
Characterizing Implicit Bias in Terms of Optimization Geometry. CoRR abs/1802.08246 (2018) - [i35]Maziar Sanjabi, Jimmy Ba, Meisam Razaviyayn, Jason D. Lee:
Solving Approximate Wasserstein GANs to Stationarity. CoRR abs/1802.08249 (2018) - [i34]Mingyi Hong, Jason D. Lee, Meisam Razaviyayn:
Gradient Primal-Dual Algorithm Converges to Second-Order Stationary Solutions for Nonconvex Distributed Optimization. CoRR abs/1802.08941 (2018) - [i33]Simon S. Du, Jason D. Lee:
On the Power of Over-parametrization in Neural Networks with Quadratic Activation. CoRR abs/1803.01206 (2018) - [i32]Mor Shpigel Nacson, Jason D. Lee, Suriya Gunasekar, Nathan Srebro, Daniel Soudry:
Convergence of Gradient Descent on Separable Data. CoRR abs/1803.01905 (2018) - [i31]Damek Davis, Dmitriy Drusvyatskiy, Sham M. Kakade, Jason D. Lee:
Stochastic subgradient method converges on tame functions. CoRR abs/1804.07795 (2018) - [i30]Shiyu Liang, Ruoyu Sun, Jason D. Lee, R. Srikant:
Adding One Neuron Can Eliminate All Bad Local Minima. CoRR abs/1805.08671 (2018) - [i29]Suriya Gunasekar, Jason D. Lee, Daniel Soudry, Nathan Srebro:
Implicit Bias of Gradient Descent on Linear Convolutional Networks. CoRR abs/1806.00468 (2018) - [i28]Simon S. Du, Wei Hu, Jason D. Lee:
Algorithmic Regularization in Learning Deep Homogeneous Models: Layers are Automatically Balanced. CoRR abs/1806.00900 (2018) - [i27]Sham M. Kakade, Jason D. Lee:
Provably Correct Automatic Subdifferentiation for Qualified Programs. CoRR abs/1809.08530 (2018) - [i26]Colin Wei, Jason D. Lee, Qiang Liu, Tengyu Ma:
On the Margin Theory of Feedforward Neural Networks. CoRR abs/1810.05369 (2018) - [i25]Simon S. Du, Jason D. Lee, Haochuan Li, Liwei Wang, Xiyu Zhai:
Gradient Descent Finds Global Minima of Deep Neural Networks. CoRR abs/1811.03804 (2018) - [i24]Maziar Sanjabi, Meisam Razaviyayn, Jason D. Lee:
Solving Non-Convex Non-Concave Min-Max Games Under Polyak-Łojasiewicz Condition. CoRR abs/1812.02878 (2018) - 2017
- [j4]Jason D. Lee, Qiang Liu, Yuekai Sun, Jonathan E. Taylor:
Communication-efficient Sparse Regression. J. Mach. Learn. Res. 18: 5:1-5:30 (2017) - [j3]Jason D. Lee, Qihang Lin, Tengyu Ma, Tianbao Yang:
Distributed Stochastic Variance Reduced Gradient Methods by Sampling Extra Data with Replacement. J. Mach. Learn. Res. 18: 122:1-122:43 (2017) - [c21]Yuchen Zhang, Jason D. Lee, Martin J. Wainwright, Michael I. Jordan:
On the Learnability of Fully-Connected Neural Networks. AISTATS 2017: 83-91 - [c20]Qiang Liu, Jason D. Lee:
Black-box Importance Sampling. AISTATS 2017: 952-961 - [c19]Jialei Wang, Jason D. Lee, Mehrdad Mahdavi, Mladen Kolar, Nati Srebro:
Sketching Meets Random Projection in the Dual: A Provable Recovery Algorithm for Big and High-dimensional Data. AISTATS 2017: 1150-1158 - [c18]Simon S. Du, Chi Jin, Jason D. Lee, Michael I. Jordan, Aarti Singh, Barnabás Póczos:
Gradient Descent Can Take Exponential Time to Escape Saddle Points. NIPS 2017: 1067-1077 - [i23]Adel Javanmard, Jason D. Lee:
A Flexible Framework for Hypothesis Testing in High-dimensions. CoRR abs/1704.07971 (2017) - [i22]Simon S. Du, Chi Jin, Jason D. Lee, Michael I. Jordan, Barnabás Póczos, Aarti Singh:
Gradient Descent Can Take Exponential Time to Escape Saddle Points. CoRR abs/1705.10412 (2017) - [i21]Mahdi Soltanolkotabi, Adel Javanmard, Jason D. Lee:
Theoretical insights into the optimization landscape of over-parameterized shallow neural networks. CoRR abs/1707.04926 (2017) - [i20]Xuanqing Liu, Cho-Jui Hsieh, Jason D. Lee, Yuekai Sun:
An inexact subsampled proximal Newton-type method for large-scale machine learning. CoRR abs/1708.08552 (2017) - [i19]Simon S. Du, Jason D. Lee, Yuandong Tian:
When is a Convolutional Filter Easy To Learn? CoRR abs/1709.06129 (2017) - [i18]Jason D. Lee, Ioannis Panageas, Georgios Piliouras, Max Simchowitz, Michael I. Jordan, Benjamin Recht:
First-order Methods Almost Always Avoid Saddle Points. CoRR abs/1710.07406 (2017) - [i17]Rong Ge, Jason D. Lee, Tengyu Ma:
Learning One-hidden-layer Neural Networks with Landscape Design. CoRR abs/1711.00501 (2017) - [i16]Simon S. Du, Jason D. Lee, Yuandong Tian, Barnabás Póczos, Aarti Singh:
Gradient Descent Learns One-hidden-layer CNN: Don't be Afraid of Spurious Local Minima. CoRR abs/1712.00779 (2017) - 2016
- [c17]Jason D. Lee, Max Simchowitz, Michael I. Jordan, Benjamin Recht:
Gradient Descent Only Converges to Minimizers. COLT 2016: 1246-1257 - [c16]Qiang Liu, Jason D. Lee, Michael I. Jordan:
A Kernelized Stein Discrepancy for Goodness-of-fit Tests. ICML 2016: 276-284 - [c15]Yuchen Zhang, Jason D. Lee, Michael I. Jordan:
L1-regularized Neural Networks are Improperly Learnable in Polynomial Time. ICML 2016: 993-1001 - [c14]Rong Ge, Jason D. Lee, Tengyu Ma:
Matrix Completion has No Spurious Local Minimum. NIPS 2016: 2973-2981 - [i15]Jason D. Lee, Max Simchowitz, Michael I. Jordan, Benjamin Recht:
Gradient Descent Converges to Minimizers. CoRR abs/1602.04915 (2016) - [i14]Rong Ge, Jason D. Lee, Tengyu Ma:
Matrix Completion has No Spurious Local Minimum. CoRR abs/1605.07272 (2016) - [i13]Michael I. Jordan, Jason D. Lee, Yun Yang:
Communication-efficient distributed statistical learning. CoRR abs/1605.07689 (2016) - [i12]Jialei Wang, Jason D. Lee, Mehrdad Mahdavi, Mladen Kolar, Nathan Srebro:
Sketching Meets Random Projection in the Dual: A Provable Recovery Algorithm for Big and High-dimensional Data. CoRR abs/1610.03045 (2016) - 2015
- [j2]Trevor Hastie, Rahul Mazumder, Jason D. Lee, Reza Zadeh:
Matrix completion and low-rank SVD via fast alternating least squares. J. Mach. Learn. Res. 16: 3367-3402 (2015) - [c13]Jason D. Lee, Yuekai Sun, Jonathan E. Taylor:
Evaluating the statistical significance of biclusters. NIPS 2015: 1324-1332 - [i11]Jason D. Lee, Yuekai Sun, Qiang Liu, Jonathan E. Taylor:
Communication-efficient sparse regression: a one-shot approach. CoRR abs/1503.04337 (2015) - [i10]Jason D. Lee:
Selective Inference and Learning Mixed Graphical Models. CoRR abs/1507.00039 (2015) - [i9]Jason D. Lee, Tengyu Ma, Qihang Lin:
Distributed Stochastic Variance Reduced Gradient Methods. CoRR abs/1507.07595 (2015) - [i8]Yuchen Zhang, Jason D. Lee, Michael I. Jordan:
ℓ1-regularized Neural Networks are Improperly Learnable in Polynomial Time. CoRR abs/1510.03528 (2015) - [i7]Yuchen Zhang, Jason D. Lee, Martin J. Wainwright, Michael I. Jordan:
Learning Halfspaces and Neural Networks with Random Initialization. CoRR abs/1511.07948 (2015) - 2014
- [j1]Jason D. Lee
Proximal Newton-Type Methods for Minimizing Composite Functions. SIAM J. Optim. 24(3): 1420-1443 (2014) - [c12]Jason D. Lee, Jonathan E. Taylor:
Exact Post Model Selection Inference for Marginal Screening. NIPS 2014: 136-144 - [c11]Austin R. Benson, Jason D. Lee, Bartek Rajwa, David F. Gleich:
Scalable Methods for Nonnegative Matrix Factorizations of Near-separable Tall-and-skinny Matrices. NIPS 2014: 945-953 - [i6]Jason D. Lee, Jonathan E. Taylor:
Exact Post Model Selection Inference for Marginal Screening. CoRR abs/1402.5596 (2014) - [i5]Austin R. Benson, Jason D. Lee, Bartek Rajwa, David F. Gleich:
Scalable methods for nonnegative matrix factorizations of near-separable tall-and-skinny matrices. CoRR abs/1402.6964 (2014) - 2013
- [c10]Jason D. Lee, Trevor Hastie:
Structure Learning of Mixed Graphical Models. AISTATS 2013: 388-396 - [c9]Jason D. Lee, Ran Gilad-Bachrach, Rich Caruana:
Using multiple samples to learn mixture models. NIPS 2013: 324-332 - [c8]Jason D. Lee, Yuekai Sun, Jonathan E. Taylor:
On model selection consistency of penalized M-estimators: a geometric theory. NIPS 2013: 342-350 - [i4]Jason D. Lee, Yuekai Sun, Jonathan E. Taylor:
On model selection consistency of regularized M-estimators. CoRR abs/1305.7477 (2013) - [i3]Jason D. Lee, Ran Gilad-Bachrach, Rich Caruana:
Using Multiple Samples to Learn Mixture Models. CoRR abs/1311.7184 (2013) - 2012
- [c7]Jason D. Lee, Yuekai Sun, Michael A. Saunders:
Proximal Newton-type methods for convex optimization. NIPS 2012: 836-844 - [i2]Jason D. Lee, Trevor Hastie:
Learning Mixed Graphical Models. CoRR abs/1205.5012 (2012) - [i1]Jason D. Lee, Yuekai Sun, Michael A. Saunders:
Proximal Newton-type Methods for Minimizing Convex Objective Functions in Composite Form. CoRR abs/1206.1623 (2012) - 2010
- [c6]Jason D. Lee, Ben Recht, Ruslan Salakhutdinov, Nathan Srebro, Joel A. Tropp:
Practical Large-Scale Optimization for Max-norm Regularization. NIPS 2010: 1297-1305
2000 – 2009
- 2009
- [c5]Jason D. Lee, Rabi N. Mahapatra, Praveen Bhojwani:
A distributed concurrent on-line test scheduling protocol for many-core NoC-based systems. ICCD 2009: 179-185 - 2008
- [c4]Jason D. Lee, Rabi N. Mahapatra:
In-field NoC-based SoC testing with distributed test vector storage. ICCD 2008: 206-211 - [c3]Jason D. Lee, Nikhil Gupta, Praveen Bhojwani, Rabi N. Mahapatra:
An On-Demand Test Triggering Mechanism for NoC-Based Safety-Critical Systems. ISQED 2008: 184-189 - 2007
- [c2]Jason D. Lee, Praveen Bhojwani, Rabi N. Mahapatra:
A Safety Analysis Framework for COTS Microprocessors in Safety-Critical Applications. HASE 2007: 407-408 - [c1]Praveen Bhojwani, Jason D. Lee, Rabi N. Mahapatra:
SAPP: scalable and adaptable peak power management in nocs. ISLPED 2007: 340-345
Coauthor Index
manage site settings
To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.
Unpaywalled article links
Add open access links from to the list of external document links (if available).
Privacy notice: By enabling the option above, your browser will contact the API of unpaywall.org to load hyperlinks to open access articles. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Unpaywall privacy policy.
Archived links via Wayback Machine
For web page which are no longer available, try to retrieve content from the of the Internet Archive (if available).
Privacy notice: By enabling the option above, your browser will contact the API of archive.org to check for archived content of web pages that are no longer available. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Internet Archive privacy policy.
Reference lists
Add a list of references from ,
, and
to record detail pages.
load references from crossref.org and opencitations.net
Privacy notice: By enabling the option above, your browser will contact the APIs of crossref.org, opencitations.net, and semanticscholar.org to load article reference information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Crossref privacy policy and the OpenCitations privacy policy, as well as the AI2 Privacy Policy covering Semantic Scholar.
Citation data
Add a list of citing articles from and
to record detail pages.
load citations from opencitations.net
Privacy notice: By enabling the option above, your browser will contact the API of opencitations.net and semanticscholar.org to load citation information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the OpenCitations privacy policy as well as the AI2 Privacy Policy covering Semantic Scholar.
OpenAlex data
Load additional information about publications from .
Privacy notice: By enabling the option above, your browser will contact the API of openalex.org to load additional information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the information given by OpenAlex.
last updated on 2024-12-01 01:13 CET by the dblp team
all metadata released as open data under CC0 1.0 license
see also: Terms of Use | Privacy Policy | Imprint
dblp was originally created in 1993 at:
since 2018, dblp has been operated and maintained by:
the dblp computer science bibliography is funded and supported by: