Low-rank MDPs with Continuous Action Spaces M Oprescu, A Bennett, N Kallus International Conference on Artificial Intelligence and Statistics, 4069-4077, 2024 | | 2024 |
Efficient and Sharp Off-Policy Evaluation in Robust Markov Decision Processes A Bennett, N Kallus, M Oprescu, W Sun, K Wang arXiv preprint arXiv:2404.00099, 2024 | | 2024 |
Doubly-valid/doubly-sharp sensitivity analysis for causal inference with unmeasured confounding J Dorn, K Guo, N Kallus Journal of the American Statistical Association, 1-23, 2024 | 31 | 2024 |
Fast rates for the regret of offline reinforcement learning Y Hu, N Kallus, M Uehara Mathematics of Operations Research, 2024 | 23 | 2024 |
Hessian-Free Laplace in Bayesian Deep Learning J McInerney, N Kallus arXiv preprint arXiv:2403.10671, 2024 | | 2024 |
Risk-Sensitive RL with Optimized Certainty Equivalents via Reduction to Standard RL K Wang, D Liang, N Kallus, W Sun arXiv preprint arXiv:2403.06323, 2024 | | 2024 |
Is Cosine-Similarity of Embeddings Really About Similarity? H Steck, C Ekanadham, N Kallus arXiv preprint arXiv:2403.05440, 2024 | | 2024 |
Switching the Loss Reduces the Cost in Batch Reinforcement Learning A Ayoub, K Wang, V Liu, S Robertson, J McInerney, D Liang, N Kallus, ... arXiv preprint arXiv:2403.05385, 2024 | | 2024 |
Efficient evaluation of natural stochastic policies in off-line reinforcement learning N Kallus, M Uehara Biometrika 111 (1), 51-69, 2024 | 8 | 2024 |
Learning the Covariance of Treatment Effects Across Many Weak Experiments A Bibaut, W Chou, S Ejdemyr, N Kallus arXiv preprint arXiv:2402.17637, 2024 | | 2024 |
Applied causal inference powered by ML and AI V Chernozhukov, C Hansen, N Kallus, M Spindler, V Syrgkanis rem 12 (1), 338, 2024 | 1 | 2024 |
Offline minimax soft-q-learning under realizability and partial coverage M Uehara, N Kallus, JD Lee, W Sun Advances in Neural Information Processing Systems 36, 2024 | 2 | 2024 |
Future-dependent value-based off-policy evaluation in pomdps M Uehara, H Kiyohara, A Bennett, V Chernozhukov, N Jiang, N Kallus, ... Advances in Neural Information Processing Systems 36, 2024 | 12 | 2024 |
More Benefits of Being Distributional: Second-Order Bounds for Reinforcement Learning K Wang, O Oertell, A Agarwal, N Kallus, W Sun arXiv preprint arXiv:2402.07198, 2024 | 2 | 2024 |
Peeking with PEAK: Sequential, Nonparametric Composite Hypothesis Tests for Means of Multiple Data Streams B Cho, K Gan, N Kallus arXiv preprint arXiv:2402.06122, 2024 | | 2024 |
Multi-Armed Bandits with Interference S Jia, P Frazier, N Kallus arXiv preprint arXiv:2402.01845, 2024 | | 2024 |
Localized Debiased Machine Learning: Efficient Inference on Quantile Treatment Effects and Beyond N Kallus, X Mao, M Uehara Journal of Machine Learning Research 25 (16), 1-59, 2024 | 1 | 2024 |
Faster Rates for Switchback Experiments S Jia, S Bhattacharya, N Kallus, CL Yu arXiv preprint arXiv:2312.15574, 2023 | | 2023 |
The benefits of being distributional: Small-loss bounds for reinforcement learning K Wang, K Zhou, R Wu, N Kallus, W Sun Advances in Neural Information Processing Systems 36, 2023 | 6 | 2023 |
Synthetic Control Analysis of the Short-Term Impact of New York State’s Bail Elimination Act on Aggregate Crime A Zhou, A Koo, N Kallus, R Ropac, R Peterson, S Koppel, T Bergin Statistics and Public Policy 11 (1), 2267617, 2023 | 6* | 2023 |