Ray Chowdhury, Sayak

7 publications

ICML 2025 Right Now, Wrong Then: Non-Stationary Direct Preference Optimization Under Preference Drift Seongho Son, William Bankes, Sayak Ray Chowdhury, Brooks Paige, Ilija Bogunovic

AISTATS 2024 Differentially Private Reward Estimation with Preference Feedback Sayak Ray Chowdhury, Xingyu Zhou, Nagarajan Natarajan

ICML 2024 OAK: Enriching Document Representations Using Auxiliary Knowledge for Extreme Classification Shikhar Mohan, Deepak Saini, Anshul Mittal, Sayak Ray Chowdhury, Bhawna Paliwal, Jian Jiao, Manish Gupta, Manik Varma

ICML 2024 Provably Robust DPO: Aligning Language Models with Noisy Feedback Sayak Ray Chowdhury, Anush Kini, Nagarajan Natarajan

ICML 2023 Differentially Private Episodic Reinforcement Learning with Heavy-Tailed Rewards Yulian Wu, Xingyu Zhou, Sayak Ray Chowdhury, Di Wang

AISTATS 2023 Exploration in Linear Bandits with Rich Action Sets and Its Implications for Inference Debangshu Banerjee, Avishek Ghosh, Sayak Ray Chowdhury, Aditya Gopalan

UAI 2020 Active Learning of Conditional Mean Embeddings via Bayesian Optimisation Sayak Ray Chowdhury, Rafael Oliveira, Fabio Ramos