Derivative-free methods for policy optimization: Guarantees for linear quadratic systems D Malik, A Pananjady, K Bhatia, K Khamaru, P Bartlett, M Wainwright The 22nd international conference on artificial intelligence and statistics …, 2019 | 195 | 2019 |
Convergence guarantees for a class of non-convex and non-smooth optimization problems K Khamaru, MJ Wainwright Journal of Machine Learning Research 20 (154), 1-52, 2019 | 71 | 2019 |
Singularity, Misspecification, and the Convergence Rate of EM R Dwivedi*, N Ho*, K Khamaru*, MI Jordan, MJ Wainwright, B Yu arXiv preprint arXiv:1810.00828, 2018 | 61 | 2018 |
Is temporal difference learning optimal? an instance-dependent analysis K Khamaru, A Pananjady, F Ruan, MJ Wainwright, MI Jordan SIAM Journal on Mathematics of Data Science 3 (4), 1013-1040, 2021 | 51 | 2021 |
Sharp analysis of expectation-maximization for weakly identifiable models R Dwivedi, N Ho, K Khamaru, M Wainwright, M Jordan, B Yu International Conference on Artificial Intelligence and Statistics, 1866-1876, 2020 | 21 | 2020 |
A peak synchronization measure for multiple signals R Biswas, K Khamaru, KK Majumdar IEEE Transactions on Signal Processing 62 (17), 4390-4398, 2014 | 19 | 2014 |
Instance-optimality in optimal value estimation: Adaptivity via variance-reduced Q-learning K Khamaru, E Xia, MJ Wainwright, MI Jordan arXiv preprint arXiv:2106.14352, 2021 | 18 | 2021 |
Computation of the maximum likelihood estimator in low-rank factor analysis K Khamaru, R Mazumder Mathematical Programming 176, 279-310, 2019 | 17 | 2019 |
Near-optimal inference in adaptive linear regression K Khamaru, Y Deshpande, T Lattimore, L Mackey, MJ Wainwright arXiv preprint arXiv:2107.02266, 2021 | 15 | 2021 |
Instability, computational efficiency and statistical accuracy N Ho, K Khamaru, R Dwivedi, MJ Wainwright, MI Jordan, B Yu arXiv preprint arXiv:2005.11411, 2020 | 13 | 2020 |
Theoretical guarantees for EM under misspecified Gaussian mixture models R Dwivedi*, N Ho*, K Khamaru*, MJ Wainwright, ... Advances in Neural Information Processing Systems, 9704-9712, 2018 | 13 | 2018 |
Challenges with EM in application to weakly identifiable mixture models R Dwivedi*, N Ho*, K Khamaru*, MJ Wainwright, MI Jordan, B Yu arXiv preprint arXiv:1902.00194, 2019 | 8 | 2019 |
Optimal variance-reduced stochastic approximation in banach spaces W Mou, K Khamaru, MJ Wainwright, PL Bartlett, MI Jordan arXiv preprint arXiv:2201.08518, 2022 | 7 | 2022 |
Instance-dependent confidence and early stopping for reinforcement learning E Xia, K Khamaru, MJ Wainwright, MI Jordan Journal of Machine Learning Research 24 (392), 1-43, 2023 | 3 | 2023 |
Instance-dependent confidence and early stopping for reinforcement learning K Khamaru, E Xia, MJ Wainwright, MI Jordan arXiv preprint arXiv:2201.08536, 2022 | 3 | 2022 |
Semi-parametric inference based on adaptively collected data L Lin, K Khamaru, MJ Wainwright arXiv preprint arXiv:2303.02534, 2023 | 2 | 2023 |
Adaptive linear estimating equations M Ying, K Khamaru, CH Zhang Advances in Neural Information Processing Systems 36, 2024 | 1 | 2024 |
Statistical Limits of Adaptive Linear Models: Low-Dimensional Estimation and Inference L Lin, M Ying, S Ghosh, K Khamaru, CH Zhang Advances in Neural Information Processing Systems 36, 2024 | | 2024 |
Guarantees for a few structured statistical problems K Khamaru University of California, Berkeley, 2022 | | 2022 |
THE ANNALS NHO RAAZ DWIVEDI, K KHAMARU The Annals of Statistics 48 (6), 2020 | | 2020 |