Multiple stopping time POMDPs: Structural results & application in interactive advertising on social media V Krishnamurthy, A Aprem, S Bhatt Automatica 95, 385-398, 2018 | 24* | 2018 |
Oracle-free Reinforcement Learning in Mean-Field Games along a Single Sample Path MA uz Zaman, A Koppel, S Bhatt, T Başar International Conference on Artificial Intelligence and Statistics (AISTATS), 2023 | 22 | 2023 |
Sequential detection of market shocks with risk-averse CVaR social sensors V Krishnamurthy, S Bhatt IEEE Journal of Selected Topics in Signal Processing 10 (6), 1061-1072, 2016 | 18 | 2016 |
Nearly optimal Catoni’s M-estimator for infinite variance S Bhatt, G Fang, P Li, G Samorodnitsky International Conference on Machine Learning (ICML) 162, 1925-1944, 2022 | 16 | 2022 |
Min-max time consensus tracking over directed trees AK Mulla, S Bhatt, DU Patil, D Chakraborty The 21st International Symposium on Mathematical Theory of Networks and …, 2014 | 15 | 2014 |
Policy gradient using weak derivatives for reinforcement learning S Bhatt, A Koppel, V Krishnamurthy 2019 IEEE 58th Conference on Decision and Control (CDC), 5531-5537, 2019 | 13 | 2019 |
Tracking infection diffusion in social networks: Filtering algorithms and threshold bounds V Krishnamurthy, S Bhatt, T Pedersen IEEE Transactions on Signal and Information Processing over Networks 3 (2 …, 2017 | 13 | 2017 |
Extreme Bandits using Robust Statistics S Bhatt, P Li, G Samorodnitsky IEEE Transactions on Information Theory (TIT) 69 (3), 1761 - 1776, 2022 | 10 | 2022 |
Offline Change Detection under Contamination S Bhatt, G Fang, P Li The 38th Conference on Uncertainty in Artificial Intelligence (UAI), 2022 | 7 | 2022 |
Minimax M-estimation under Adversarial Contamination S Bhatt, G Fang, P Li, G Samorodnitsky International Conference on Machine Learning (ICML) 162, 1906-1924, 2022 | 5 | 2022 |
Minimax M-estimation under adversarial corruption S Bhatt, G Fang, P Li, G Samorodnitsky Proceedings of the 39th International Conference on Machine Learning (ICML …, 2022 | 5 | 2022 |
Controlled sequential information fusion with social sensors S Bhatt, V Krishnamurthy IEEE Transactions on Automatic Control (TAC) 66 (12), 5893-5908, 2020 | 5 | 2020 |
Adversarial linear-quadratic mean-field games over multigraphs MAU Zaman, S Bhatt, T Başar 2021 60th IEEE Conference on Decision and Control (CDC), 209-214, 2021 | 4 | 2021 |
Adaptive polling in hierarchical social networks using blackwell dominance S Bhatt, V Krishnamurthy IEEE Transactions on Signal and Information Processing over Networks 5 (3 …, 2019 | 4 | 2019 |
Semiparametric information state embedding for policy search under imperfect information S Bhatt, W Mao, A Koppel, T Başar 2021 60th IEEE Conference on Decision and Control (CDC), 4501-4506, 2021 | 3 | 2021 |
Controlled information fusion with risk-averse CVaR social sensors S Bhatt, V Krishnamurthy 2017 IEEE 56th Annual Conference on Decision and Control (CDC), 2605-2610, 2017 | 3 | 2017 |
Online MCMC thinning with kernelized Stein discrepancy A Koppel, J Eappen, S Bhatt, C Hawkins, S Ganesh SIAM Journal on Mathematics of Data Science 6 (1), 51-75, 2024 | 2 | 2024 |
Piecewise stationary bandits under risk criteria S Bhatt, G Fang, P Li International Conference on Artificial Intelligence and Statistics (AISTATS …, 2023 | 2 | 2023 |
Regret Analysis for RL using Renewal Bandit Feedback S Bhatt, G Fang, P Li, G Samorodnitsky 2022 IEEE Information Theory Workshop (ITW), 137-142, 2022 | 2 | 2022 |
Catoni-style Confidence Sequences under Infinite Variance S Bhatt, G Fang, P Li, G Samorodnitsky arXiv preprint arXiv:2208.03185, 2022 | 2 | 2022 |