Derivative-free methods for policy optimization: Guarantees for linear quadratic systems D Malik, A Pananjady, K Bhatia, K Khamaru, PL Bartlett, MJ Wainwright Journal of Machine Learning Research 21 (21), 1-51, 2020 | 208 | 2020 |
Gradient diversity: a key ingredient for scalable distributed learning D Yin, A Pananjady, M Lam, D Papailiopoulos, K Ramchandran, P Bartlett Proceedings of the 21th International Conference on Artificial Intelligence …, 2017 | 156 | 2017 |
Linear regression with shuffled data: Statistical and computational limits of permutation recovery A Pananjady, MJ Wainwright, TA Courtade IEEE Transactions on Information Theory 64 (5), 3286-3300, 2017 | 154* | 2017 |
Denoising linear models with permuted data A Pananjady, MJ Wainwright, TA Courtade 2017 IEEE International Symposium on Information Theory (ISIT), 446-450, 2017 | 98 | 2017 |
Existence of Stein kernels under a spectral gap, and discrepancy bounds TA Courtade, M Fathi, A Pananjady | 74 | 2019 |
Instance-Dependent ℓ∞-Bounds for Policy Evaluation in Tabular Reinforcement Learning A Pananjady, MJ Wainwright IEEE Transactions on Information Theory 67 (1), 566-585, 2020 | 70* | 2020 |
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 | 64 | 2021 |
Optimally approximating the coverage lifetime of wireless sensor networks A Pananjady, VK Bagaria, R Vaze IEEE/ACM Transactions on Networking 25 (1), 98-111, 2016 | 58* | 2016 |
Worst-case versus average-case design for estimation from partial pairwise comparisons A Pananjady, C Mao, V Muthukumar, MJ Wainwright, TA Courtade The Annals of Statistics 48 (2), 1072-1097, 2020 | 43* | 2020 |
Max-affine regression: Parameter estimation for Gaussian designs A Ghosh, A Pananjady, A Guntuboyina, K Ramchandran IEEE Transactions on Information Theory 68 (3), 1851-1885, 2021 | 42* | 2021 |
Isotonic regression with unknown permutations: Statistics, computation and adaptation A Pananjady, RJ Samworth The Annals of Statistics 50 (1), 324-350, 2022 | 33 | 2022 |
Quantitative Stability of the Entropy Power Inequality TA Courtade, M Fathi, A Pananjady IEEE Transactions on Information Theory 64 (8), 5691-5703, 2018 | 31 | 2018 |
Optimal oracle inequalities for projected fixed-point equations, with applications to policy evaluation W Mou, A Pananjady, MJ Wainwright Mathematics of Operations Research 48 (4), 2308-2336, 2023 | 25* | 2023 |
Optimal and instance-dependent guarantees for Markovian linear stochastic approximation W Mou, A Pananjady, MJ Wainwright, PL Bartlett Mathematical Statistics and Learning 7 (1), 41-153, 2024 | 24 | 2024 |
Sharp global convergence guarantees for iterative nonconvex optimization with random data KA Chandrasekher, A Pananjady, C Thrampoulidis The Annals of Statistics 51 (1), 179-210, 2023 | 24* | 2023 |
Towards optimal estimation of bivariate isotonic matrices with unknown permutations C Mao, A Pananjady, MJ Wainwright The Annals of Statistics 48 (6), 3183-3205, 2020 | 24 | 2020 |
A family of Bayesian Cramér-Rao bounds, and consequences for log-concave priors E Aras, KY Lee, A Pananjady, TA Courtade 2019 IEEE International Symposium on Information Theory (ISIT), 2699-2703, 2019 | 24 | 2019 |
The Effect of Local Decodability Constraints on Variable-Length Compression A Pananjady, TA Courtade IEEE Transactions on Information Theory 64 (4), 2593-2608, 2018 | 20* | 2018 |
Wasserstein stability of the entropy power inequality for log-concave random vectors TA Courtade, M Fathi, A Pananjady 2017 IEEE International Symposium on Information Theory (ISIT), 659-663, 2017 | 17* | 2017 |
Accelerated and instance-optimal policy evaluation with linear function approximation T Li, G Lan, A Pananjady SIAM Journal on Mathematics of Data Science 5 (1), 174-200, 2023 | 16 | 2023 |