Jason D. Lee
Princeton University
H-index: 57
North America-United States
Top articles of Jason D. Lee
Title | Journal | Author(s) | Publication Date |
---|---|---|---|
Medusa: Simple llm inference acceleration framework with multiple decoding heads | arXiv preprint arXiv:2401.10774 | Tianle Cai Yuhong Li Zhengyang Geng Hongwu Peng Jason D Lee | 2024/1/19 |
Reward-agnostic fine-tuning: Provable statistical benefits of hybrid reinforcement learning | Advances in Neural Information Processing Systems | Gen Li Wenhao Zhan Jason D Lee Yuejie Chi Yuxin Chen | 2024/2/13 |
Smoothing the landscape boosts the signal for sgd: Optimal sample complexity for learning single index models | Advances in Neural Information Processing Systems | Alex Damian Eshaan Nichani Rong Ge Jason D Lee | 2024/2/13 |
Fine-tuning language models with just forward passes | Advances in Neural Information Processing Systems | Sadhika Malladi Tianyu Gao Eshaan Nichani Alex Damian Jason D Lee | 2024/2/13 |
Provable guarantees for nonlinear feature learning in three-layer neural networks | Advances in Neural Information Processing Systems | Eshaan Nichani Alex Damian Jason D Lee | 2024/2/13 |
Implicit bias of gradient descent for logistic regression at the edge of stability | Advances in Neural Information Processing Systems | Jingfeng Wu Vladimir Braverman Jason D Lee | 2024/2/13 |
Offline minimax soft-q-learning under realizability and partial coverage | Advances in Neural Information Processing Systems | Masatoshi Uehara Nathan Kallus Jason D Lee Wen Sun | 2024/2/13 |
Understanding incremental learning of gradient descent: A fine-grained analysis of matrix sensing | Jikai Jin Zhiyuan Li Kaifeng Lyu Simon Shaolei Du Jason D Lee | 2023/7/3 | |
Reconstructing training data from model gradient, provably | Zihan Wang Jason Lee Qi Lei | 2023/4/11 | |
Looped transformers as programmable computers | Angeliki Giannou Shashank Rajput Jy-yong Sohn Kangwook Lee Jason D Lee | 2023/7/3 | |
Optimal multi-distribution learning | arXiv preprint arXiv:2312.05134 | Zihan Zhang Wenhao Zhan Yuxin Chen Simon S Du Jason D Lee | 2023/12/8 |
Can We Find Nash Equilibria at a Linear Rate in Markov Games? | arXiv preprint arXiv:2303.03095 | Zhuoqing Song Jason D Lee Zhuoran Yang | 2023/3/3 |
Computationally efficient pac rl in pomdps with latent determinism and conditional embeddings | Masatoshi Uehara Ayush Sekhari Jason D Lee Nathan Kallus Wen Sun | 2023/7/3 | |
Rest: Retrieval-based speculative decoding | arXiv preprint arXiv:2311.08252 | Zhenyu He Zexuan Zhong Tianle Cai Jason D Lee Di He | 2023/11/14 |
Policy mirror descent for regularized reinforcement learning: A generalized framework with linear convergence | SIAM Journal on Optimization | Wenhao Zhan Shicong Cen Baihe Huang Yuxin Chen Jason D Lee | 2023/6/30 |
Settling the sample complexity of online reinforcement learning | arXiv preprint arXiv:2307.13586 | Zihan Zhang Yuxin Chen Jason D Lee Simon S Du | 2023/7/25 |
How to Query Human Feedback Efficiently in RL? | arXiv preprint arXiv:2305.18505 | Wenhao Zhan Masatoshi Uehara Wen Sun Jason D Lee | 2023/5/29 |
Teaching arithmetic to small transformers | arXiv preprint arXiv:2307.03381 | Nayoung Lee Kartik Sreenivasan Jason D Lee Kangwook Lee Dimitris Papailiopoulos | 2023/7/7 |
Provable offline reinforcement learning with human feedback | arXiv preprint arXiv:2305.14816 | Wenhao Zhan Masatoshi Uehara Nathan Kallus Jason D Lee Wen Sun | 2023/5/24 |
Nearly minimax algorithms for linear bandits with shared representation | arXiv preprint arXiv:2203.15664 | Jiaqi Yang Qi Lei Jason D Lee Simon S Du | 2022/3/29 |