SAYAK RAY CHOWDHURY
Affiliation: Postdoctoral Researcher, Microsoft Research, India
Email: t-sayakr@microsoft.com
Research Interests: Theoretical Machine Learning including
Online Learning: Multi-armed Bandits, Reinforcement Learning, Bayesian Optimization
Differential Privacy: Privacy Preserving Machine Learning
Learning Theory: Model Selection, Concentration Inequalities
About me: I am a Postdoctoral Researcher at Microsoft Research, India where I am hosted by Dr. Nagarajan Natarajan. I work in Theoretical Machine Learning with a focus on (a) Sequential Decision making in Multi-armed Bandits and Reinforcement Learning framework and (b) Privacy Preserving Machine Learning in the Differential Privacy framework.
Previously, I was a Postdoctoral fellow at Dept. of Systems Engineering, Boston University. Prior to that, I did my PhD from the ECE Dept. of Indian Institute of Science, Bangalore where I was advised by Prof. Aditya Gopalan. I spent the summer of 2019 working at Google, Sunnyvale, USA. I did my masters from Indian Institute of Science, Bangalore and bachelor's from Jadavpur University. Here are my CV, my Google Scholar profile and my Semantic Scholar profile.
Updates:
March 5: Invited talk on Aligning Language Models with Noisy Preferences at Center for Networked Intelligence, IISc Bangalore
Jan 20: Paper on private reward model training accepted at AISTATS, 2024.
Jan 16: Paper on federated bandits accepted at ICLR, 2024.
Oct 31: Paper on Generator Augmented Retrieval models for Information Retrieval uploaded in arxiv.
Aug 18: Invited talk on Differential Privacy and Multi-armed Bandits at Dept. of CSA, IISc Bangalore.
June 06: Invited talk on Differential Privacy and Reinforcement Learning at Jagiellonian University, Krakow, Poland.
Selected Publications (see full list here):
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
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
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
No-regret Algorithms for Multi-task Bayesian Optimization. Sayak Ray Chowdhury, Aditya Gopalan. International Conference on Artificial Intelligence and Statistics (AISTATS), 2021. 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