Sayak Ray Chowdhury

55 papers A* 13A 7B 1C 1Journal 31Unranked 2

Year	Rank	Type	Title / Venue / Authors
2026	A*	`conf`	DP-NCB: Privacy Preserving Fair Bandits. AAAI Dhruv Sarkar, Nishant Pandey, Sayak Ray Chowdhury
2026	J	`jnl`	Improved Algorithms for Nash Welfare in Linear Bandits. CoRR Dhruv Sarkar, Nishant Pandey, Sayak Ray Chowdhury
2025	—	`conf`	Active Preference Optimization for Sample Efficient RLHF. ECML/PKDD (5) Nirjhar Das, Souradip Chakraborty, Aldo Pacchiano, Sayak Ray Chowdhury
2025	J	`jnl`	Communication Efficient Secure and Private Multi-Party Deep Learning. Proc. Priv. Enhancing Technol. Sankha Das, Sayak Ray Chowdhury, Nishanth Chandran, Divya Gupta, Satya Lokam, Rahul Sharma
2025	J	`jnl`	Constrained Adversarial Perturbation. CoRR Virendra Nishad, Bhaskar Mukhoty, Hilal AlQuabeh, Sandeep K. Shukla, Sayak Ray Chowdhury
2025	J	`jnl`	DP-NCB: Privacy Preserving Fair Bandits. CoRR Dhruv Sarkar, Nishant Pandey, Sayak Ray Chowdhury
2025	J	`jnl`	KITE: Kernelized and Information Theoretic Exemplars for In-Context Learning. CoRR Vaibhav Singh, Soumya Suvra Ghosal, Kapu Nirmal Joshua, Soumyabrata Pal, Sayak Ray Chowdhury
2025	J	`jnl`	Revisiting Social Welfare in Bandits: UCB is (Nearly) All You Need. CoRR Dhruv Sarkar, Nishant Pandey, Sayak Ray Chowdhury
2025	A*	`conf`	Right Now, Wrong Then: Non-Stationary Direct Preference Optimization under Preference Drift. ICML Seongho Son, William Bankes, Sayak Ray Chowdhury, Brooks Paige, Ilija Bogunovic
2025	J	`jnl`	Why DPO is a Misspecified Estimator and How to Fix It. CoRR Aditya Gopalan, Sayak Ray Chowdhury, Debangshu Banerjee
2024	J	`jnl`	Communication Efficient Secure and Private Multi-Party Deep Learning. IACR Cryptol. ePrint Arch. Sankha Das, Sayak Ray Chowdhury, Nishanth Chandran, Divya Gupta, Satya Lokam, Rahul Sharma
2024	A	`conf`	Differentially Private Reward Estimation with Preference Feedback. AISTATS Sayak Ray Chowdhury, Xingyu Zhou, Nagarajan Natarajan
2024	A*	`conf`	OAK: Enriching Document Representations using Auxiliary Knowledge for Extreme Classification. ICML Shikhar Mohan, Deepak Saini, Anshul Mittal, Sayak Ray Chowdhury, Bhawna Paliwal, Jian Jiao, Manish Gupta, Manik Varma
2024	A*	`conf`	On Differentially Private Federated Linear Contextual Bandits. ICLR Xingyu Zhou, Sayak Ray Chowdhury
2024	A*	`conf`	Provably Robust DPO: Aligning Language Models with Noisy Feedback. ICML Sayak Ray Chowdhury, Anush Kini, Nagarajan Natarajan
2024	J	`jnl`	Provably Robust DPO: Aligning Language Models with Noisy Feedback. CoRR Sayak Ray Chowdhury, Anush Kini, Nagarajan Natarajan
2024	J	`jnl`	Provably Sample Efficient RLHF via Active Preference Optimization. CoRR Nirjhar Das, Souradip Chakraborty, Aldo Pacchiano, Sayak Ray Chowdhury
2024	J	`jnl`	Right Now, Wrong Then: Non-Stationary Direct Preference Optimization under Preference Drift. CoRR Seongho Son, William Bankes, Sayak Ray Chowdhury, Brooks Paige, Ilija Bogunovic
2023	A*	`conf`	Bregman Deviations of Generic Exponential Families. COLT Sayak Ray Chowdhury, Patrick Saux, Odalric Maillard, Aditya Gopalan
2023	A	`conf`	Combinatorial categorized bandits with expert rankings. UAI Sayak Ray Chowdhury, Gaurav Sinha, Nagarajan Natarajan, Amit Sharma
2023	A*	`conf`	Differentially Private Episodic Reinforcement Learning with Heavy-tailed Rewards. ICML Yulian Wu, Xingyu Zhou, Sayak Ray Chowdhury, Di Wang
2023	J	`jnl`	Differentially Private Episodic Reinforcement Learning with Heavy-tailed Rewards. CoRR Yulian Wu, Xingyu Zhou, Sayak Ray Chowdhury, Di Wang
2023	J	`jnl`	Differentially Private Reward Estimation with Preference Feedback. CoRR Sayak Ray Chowdhury, Xingyu Zhou, Nagarajan Natarajan
2023	A*	`conf`	Distributed Differential Privacy in Multi-Armed Bandits. ICLR Sayak Ray Chowdhury, Xingyu Zhou
2023	A	`conf`	Exploration in Linear Bandits with Rich Action Sets and its Implications for Inference. AISTATS Debangshu Banerjee, Avishek Ghosh, Sayak Ray Chowdhury, Aditya Gopalan
2023	J	`jnl`	GAR-meets-RAG Paradigm for Zero-Shot Information Retrieval. CoRR Daman Arora, Anush Kini, Sayak Ray Chowdhury, Nagarajan Natarajan, Gaurav Sinha, Amit Sharma
2023	J	`jnl`	On Differentially Private Federated Linear Contextual Bandits. CoRR Xingyu Zhou, Sayak Ray Chowdhury
2022	J	`jnl`	Bregman Deviations of Generic Exponential Families. CoRR Sayak Ray Chowdhury, Patrick Saux, Odalric-Ambrym Maillard, Aditya Gopalan
2022	A*	`conf`	Differentially Private Regret Minimization in Episodic Markov Decision Processes. AAAI Sayak Ray Chowdhury, Xingyu Zhou
2022	J	`jnl`	Distributed Differential Privacy in Multi-Armed Bandits. CoRR Sayak Ray Chowdhury, Xingyu Zhou
2022	J	`jnl`	Exploration in Linear Bandits with Rich Action Sets and its Implications for Inference. CoRR Debangshu Banerjee, Avishek Ghosh, Sayak Ray Chowdhury, Aditya Gopalan
2022	—	`conf`	Model Selection in Reinforcement Learning with General Function Approximations. ECML/PKDD (4) Avishek Ghosh, Sayak Ray Chowdhury
2022	J	`jnl`	Model Selection in Reinforcement Learning with General Function Approximations. CoRR Avishek Ghosh, Sayak Ray Chowdhury
2022	A*	`conf`	Shuffle Private Linear Contextual Bandits. ICML Sayak Ray Chowdhury, Xingyu Zhou
2022	J	`jnl`	Shuffle Private Linear Contextual Bandits. CoRR Sayak Ray Chowdhury, Xingyu Zhou
2022	C	`conf`	Value Function Approximations via Kernel Embeddings for No-Regret Reinforcement Learning. ACML Sayak Ray Chowdhury, Rafael Oliveira
2021	B	`conf`	Adaptive Control of Differentially Private Linear Quadratic Systems. ISIT Sayak Ray Chowdhury, Xingyu Zhou, Ness B. Shroff
2021	J	`jnl`	Adaptive Control of Differentially Private Linear Quadratic Systems. CoRR Sayak Ray Chowdhury, Xingyu Zhou, Ness B. Shroff
2021	J	`jnl`	Differentially Private Regret Minimization in Episodic Markov Decision Processes. CoRR Sayak Ray Chowdhury, Xingyu Zhou
2021	J	`jnl`	Model Selection with Near Optimal Rates for Reinforcement Learning with General Model Classes. CoRR Avishek Ghosh, Sayak Ray Chowdhury, Kannan Ramchandran
2021	A	`conf`	No-regret Algorithms for Multi-task Bayesian Optimization. AISTATS Sayak Ray Chowdhury, Aditya Gopalan
2021	A	`conf`	Reinforcement Learning in Parametric MDPs with Exponential Families. AISTATS Sayak Ray Chowdhury, Aditya Gopalan, Odalric-Ambrym Maillard
2020	A	`conf`	Active Learning of Conditional Mean Embeddings via Bayesian Optimisation. UAI Sayak Ray Chowdhury, Rafael Oliveira, Fabio Ramos
2020	J	`jnl`	No-Regret Reinforcement Learning with Value Function Approximation: a Kernel Embedding Approach. CoRR Sayak Ray Chowdhury, Rafael Oliveira
2020	J	`jnl`	No-regret Algorithms for Multi-task Bayesian Optimization. CoRR Sayak Ray Chowdhury, Aditya Gopalan
2019	A*	`conf`	Bayesian Optimization under Heavy-tailed Payoffs. NeurIPS Sayak Ray Chowdhury, Aditya Gopalan
2019	J	`jnl`	Bayesian Optimization under Heavy-tailed Payoffs. CoRR Sayak Ray Chowdhury, Aditya Gopalan
2019	J	`jnl`	On Batch Bayesian Optimization. CoRR Sayak Ray Chowdhury, Aditya Gopalan
2019	J	`jnl`	On Online Learning in Kernelized Markov Decision Processes. CoRR Sayak Ray Chowdhury, Aditya Gopalan
2019	A	`conf`	Online Learning in Kernelized Markov Decision Processes. AISTATS Sayak Ray Chowdhury, Aditya Gopalan
2018	J	`jnl`	Online Learning in Kernelized Markov Decision Processes. CoRR Sayak Ray Chowdhury, Aditya Gopalan
2017	A*	`conf`	Misspecified Linear Bandits. AAAI Avishek Ghosh, Sayak Ray Chowdhury, Aditya Gopalan
2017	J	`jnl`	Misspecified Linear Bandits. CoRR Avishek Ghosh, Sayak Ray Chowdhury, Aditya Gopalan
2017	A*	`conf`	On Kernelized Multi-armed Bandits. ICML Sayak Ray Chowdhury, Aditya Gopalan
2017	J	`jnl`	On Kernelized Multi-armed Bandits. CoRR Sayak Ray Chowdhury, Aditya Gopalan