Research
PREPRINTS
Provably Robust DPO: Aligning Language Models with Noisy Feedback. Sayak Ray Chowdhury, Anush Kini, Nagarajan Natarajan. 2024. Link
Provably Sample Efficient RLHF via Active Preference Optimization. Nirjhar Das, Souradip Chakraborty, Aldo Pacchiano, Sayak Ray Chowdhury. 2024. Link
GAR-meets-RAG Paradigm for Zero-Shot Information Retrieval. Daman Arora, Anush Kini, Sayak Ray Chowdhury, Nagarajan Natarajan, Gaurav Sinha, Amit Sharma. 2023. Link
Publications
2024
Differentially Private Federated Linear Contextual Bandits. Xingyu Zhou, Sayak Ray Chowdhury. International Conference on Learning Representations (ICLR), 2024. Link
Differentially Private Reward Estimation with Preference Feedback. Sayak Ray Chowdhury, Xingyu Zhou, Nagarajan Natarajan. International Conference on Artificial Intelligence and Statistics (AISTATS), 2024. Link
2023
Combinatorial Categorized Bandits with Expert Rankings. Sayak Ray Chowdhury, Gaurav Sinha, Nagarajan Natarajan, Amit Sharma. Conference on Uncertainty in Artificial Intelligence (UAI), 2023. Link
Differentially Private Episodic Reinforcement Learning with Heavy-tailed Rewards. Yulian Wu, Sayak Ray Chowdhury, Xingyu Zhou, Di Wang. International Conference on Machine Learning (ICML), 2023. Link
Bregman Deviations of Generic Exponential Families. Sayak Ray Chowdhury, Patrick Saux, Odalric-Ambrym Maillard, Aditya Gopalan. 36th Annual Conference on Learning Theory (COLT), 2023. Link
Distributed Differential Privacy in Multi-armed Bandits. Sayak Ray Chowdhury, Xingyu Zhou. International Conference on Learning Representations (ICLR), 2023. Link
Exploration in Linear Bandits with Rich Action Sets and its Implications for Inference. Debangshu Banerjee, Avishek Ghosh, Sayak Ray Chowdhury, Aditya Gopalan. International Conference on Artificial Intelligence and Statistics (AISTATS), 2023. Link
2022
Value Function Approximations via Kernel Embeddings for No-Regret Reinforcement Learning. Sayak Ray Chowdhury, Rafael Oliveira. Asian Conference on Machine Learning (ACML), 2022. Link
Model Selection in Reinforcement Learning with General Function Approximations. Avishek Ghosh, Sayak Ray Chowdhury. European Conference on Machine Learning (ECML-PKDD), 2022. Link
Shuffle Private Linear Contextual Bandits. Sayak Ray Chowdhury, Xingyu Zhou. International Conference on Machine Learning (ICML), 2022. Link
Differentially Private Regret Minimization in Episodic Markov Decision Processes. Sayak Ray Chowdhury, Xingyu Zhou. AAAI Conference on Artificial Intelligence (AAAI), 2022. Link
2017-2021
Reinforcement Learning in Parametric MDPs with Exponential Families. Sayak Ray Chowdhury, Aditya Gopalan, Odalric-Ambrym Maillard. International Conference on Artificial Intelligence and Statistics (AISTATS), 2021. Link
No-regret Algorithms for Multi-task Bayesian Optimization. Sayak Ray Chowdhury, Aditya Gopalan. International Conference on Artificial Intelligence and Statistics (AISTATS), 2021. Link
Adaptive Control of Differentially Private Linear Quadratic Systems. Sayak Ray Chowdhury, Xingyu Zhou, Ness Shroff. IEEE International Symposium on Information Theory (ISIT), 2021. Link
Active Learning of Conditional Mean Embeddings via Bayesian Optimisation. Sayak Ray Chowdhury, Rafael Oliveira, Fabio Ramos. Conference on Uncertainty in Artificial Intelligence (UAI), 2020. Link
Bayesian Optimization under Heavy-tailed Payoffs. Sayak Ray Chowdhury, Aditya Gopalan. Neural Information Processing Systems (NeurIPS), 2019. Link
Online Learning in Kernelized Markov Decision Processes. Sayak Ray Chowdhury, Aditya Gopalan. International Conference on Artificial Intelligence and Statistics (AISTATS), 2019. Link
On Kernelized Multi-armed Bandits. Sayak Ray Chowdhury, Aditya Gopalan. International Conference on Machine Learning (ICML), 2017. Link
Misspecified Linear Bandits. Avishek Ghosh, Sayak Ray Chowdhury, Aditya Gopalan. AAAI Conference on Artificial Intelligence (AAAI), 2017. Link
PEER-REVIEWED ARTICLES
Differentially Private Reward Estimation from Preference-based Feedback. Sayak Ray Chowdhury, Xingyu Zhou. ICML Workshop on The Many Facets of Preference-Based Learning, 2023. Also appeared in Theory and Practice of Differential Privacy (TPDP), Boston University, 2023.
On Differentially Private Federated Linear Contextual Bandits. Xingyu Zhou, Sayak Ray Chowdhury. ICML Workshop on Federated Learning and Analytics, 2023. Also appeared in Theory and Practice of Differential Privacy (TPDP), Boston University, 2023.
Online Contextual Learning with Limited Feedback. Sayak Ray Chowdhury, Aditya Gangrade, Ashok Cutkosky, Venkatesh Saligrama. ICML Workshop on Adaptive Experimental Design and Active Learning in the Real World, 2022. Link
Online Learning in Kernelized Markov Decision Processes. Sayak Ray Chowdhury, Aditya Gopalan. NeurIPS workshop on Infer to Control: Probabilistic Reinforcement Learning and Structured Control, 2018.
On Batch Bayesian Optimization. Sayak Ray Chowdhury, Aditya Gopalan. NeurIPS workshop on All of Bayesian Nonparametrics, 2018. Link
Theses
PhD Thesis: Online Reinforcement Learning in Large and Structured Environments. Sayak Ray Chowdhury. Department of ECE, Indian Institute of Science. July 2021.
Masters Thesis: A Game Theoretic Approach to Robust Optimization. Sayak Ray Chowdhury. Department of CSA, Indian Institute of Science. June 2015.