Akshay Krishnamurthy
University of Massachusetts Amherst
H-index: 41
North America-United States
Top articles of Akshay Krishnamurthy
Title | Journal | Author(s) | Publication Date |
---|---|---|---|
System for effective use of data for personalization | 2024/1/4 | ||
Oracle-efficient pessimism: Offline policy optimization in contextual bandits | Lequn Wang Akshay Krishnamurthy Alex Slivkins | 2024/4/18 | |
Model-free representation learning and exploration in low-rank mdps | Journal of Machine Learning Research | Aditya Modi Jinglin Chen Akshay Krishnamurthy Nan Jiang Alekh Agarwal | 2024 |
Can large language models explore in-context? | arXiv preprint arXiv:2403.15371 | Akshay Krishnamurthy Keegan Harris Dylan J Foster Cyril Zhang Aleksandrs Slivkins | 2024/3/22 |
Scalable Online Exploration via Coverability | arXiv preprint arXiv:2403.06571 | Philip Amortila Dylan J Foster Akshay Krishnamurthy | 2024/3/11 |
Exposing attention glitches with flip-flop language modeling | Advances in Neural Information Processing Systems | Bingbin Liu Jordan Ash Surbhi Goel Akshay Krishnamurthy Cyril Zhang | 2024/2/13 |
Mitigating Covariate Shift in Misspecified Regression with Applications to Reinforcement Learning | arXiv preprint arXiv:2401.12216 | Philip Amortila Tongyi Cao Akshay Krishnamurthy | 2024/1/22 |
Statistical learning under heterogenous distribution shift | Max Simchowitz Anurag Ajay Pulkit Agrawal Akshay Krishnamurthy | 2023/7/3 | |
Contextual search in the presence of adversarial corruptions | Operations Research | Akshay Krishnamurthy Thodoris Lykouris Chara Podimata Robert Schapire | 2023/7 |
Butterfly effects of sgd noise: Error amplification in behavior cloning and autoregression | arXiv preprint arXiv:2310.11428 | Adam Block Dylan J Foster Akshay Krishnamurthy Max Simchowitz Cyril Zhang | 2023/10/17 |
Robust dynamic assortment optimization in the presence of outlier customers | Operations Research | Xi Chen Akshay Krishnamurthy Yining Wang | 2023/8/21 |
Learning hidden markov models using conditional samples | Gaurav Mahajan Sham Kakade Akshay Krishnamurthy Cyril Zhang | 2023/7/12 | |
Streaming active learning with deep neural networks | Akanksha Saran Safoora Yousefi Akshay Krishnamurthy John Langford Jordan T Ash | 2023/7/3 | |
Sparsity in partially controllable linear systems | Yonathan Efroni Sham Kakade Akshay Krishnamurthy Cyril Zhang | 2022/6/28 | |
Guaranteed discovery of control-endogenous latent states with multi-step inverse models | arXiv preprint arXiv:2207.08229 | Alex Lamb Riashat Islam Yonathan Efroni Aniket Didolkar Dipendra Misra | 2022/7/17 |
Efficient and optimal algorithms for contextual dueling bandits under realizability | Aadirupa Saha Akshay Krishnamurthy | 2022/3/20 | |
Sample-efficient reinforcement learning in the presence of exogenous information | Yonathan Efroni Dylan J Foster Dipendra Misra Akshay Krishnamurthy John Langford | 2022/6/28 | |
A sharp characterization of linear estimators for offline policy evaluation | arXiv preprint arXiv:2203.04236 | Juan C Perdomo Akshay Krishnamurthy Peter Bartlett Sham Kakade | 2022/3 |
On the statistical efficiency of reward-free exploration in non-linear rl | Advances in Neural Information Processing Systems | Jinglin Chen Aditya Modi Akshay Krishnamurthy Nan Jiang Alekh Agarwal | 2022/12/6 |
Understanding contrastive learning requires incorporating inductive biases | Nikunj Saunshi Jordan Ash Surbhi Goel Dipendra Misra Cyril Zhang | 2022/6/28 |