Follow
Sayak Ray Chowdhury
Sayak Ray Chowdhury
Assistant Professor of Computer Science and Engineering, Indian Institute of Technology, Kanpur
Verified email at cse.iitk.ac.in - Homepage
Title
Cited by
Cited by
Year
On kernelized multi-armed bandits
SR Chowdhury, A Gopalan
International Conference on Machine Learning, 844-853, 2017
4902017
Misspecified linear bandits
A Ghosh, SR Chowdhury, A Gopalan
Proceedings of the AAAI Conference on Artificial Intelligence 31 (1), 2017
732017
Online learning in kernelized markov decision processes
SR Chowdhury, A Gopalan
The 22nd International Conference on Artificial Intelligence and Statistics …, 2019
532019
Bayesian optimization under heavy-tailed payoffs
S Ray Chowdhury, A Gopalan
Advances in Neural Information Processing Systems 32, 2019
302019
Shuffle private linear contextual bandits
SR Chowdhury, X Zhou
International Conference in Machine Learning, 2022., 2022
252022
Provably robust dpo: Aligning language models with noisy feedback
SR Chowdhury, A Kini, N Natarajan
ICML 2024, 2024
222024
Gar-meets-rag paradigm for zero-shot information retrieval
D Arora, A Kini, SR Chowdhury, N Natarajan, G Sinha, A Sharma
arXiv preprint arXiv:2310.20158, 2023
19*2023
Differentially private regret minimization in episodic markov decision processes
SR Chowdhury, X Zhou
Proceedings of the AAAI Conference on Artificial Intelligence 36 (6), 6375-6383, 2022
192022
No-regret algorithms for multi-task bayesian optimization
SR Chowdhury, A Gopalan
International Conference on Artificial Intelligence and Statistics, 1873-1881, 2021
182021
Provably sample efficient rlhf via active preference optimization
N Das, S Chakraborty, A Pacchiano, SR Chowdhury
arXiv preprint arXiv:2402.10500, 2024
16*2024
Bregman deviations of generic exponential families
SR Chowdhury, P Saux, O Maillard, A Gopalan
The Thirty Sixth Annual Conference on Learning Theory, 394-449, 2023
162023
Distributed Differential Privacy in Multi-Armed Bandits
SR Chowdhury, X Zhou
ICLR 2023, 2022
162022
Reinforcement learning in parametric mdps with exponential families
SR Chowdhury, A Gopalan, OA Maillard
International Conference on Artificial Intelligence and Statistics, 1855-1863, 2021
162021
Value Function Approximations via Kernel Embeddings for No-Regret Reinforcement Learning
SR Chowdhury, R Oliveira
Asian Conference on Machine Learning, 249-264, 2023
14*2023
On differentially private federated linear contextual bandits
X Zhou, SR Chowdhury
ICLR 2024, 2023
132023
On Batch Bayesian Optimization
SR Chowdhury, A Gopalan
arXiv preprint arXiv:1911.01032, 2019
92019
Model Selection in Reinforcement Learning with General Function Approximations
A Ghosh, SR Chowdhury
ECML-PKDD, 2022, 2022
8*2022
Adaptive control of differentially private linear quadratic systems
SR Chowdhury, X Zhou, N Shroff
2021 IEEE International Symposium on Information Theory (ISIT), 485-490, 2021
82021
Active learning of conditional mean embeddings via bayesian optimisation
SR Chowdhury, R Oliveira, F Ramos
Conference on Uncertainty in Artificial Intelligence, 1119-1128, 2020
82020
Exploration in Linear Bandits with Rich Action Sets and its Implications for Inference
D Banerjee, A Ghosh, SR Chowdhury, A Gopalan
International Conference on Artificial Intelligence and Statistics, 8233-8262, 2023
7*2023
The system can't perform the operation now. Try again later.
Articles 1–20