Affiliation: Assistant Professor, Department of CSE, IIT Kanpur, India
Email: sayakrc [at] cse [dot] iitk [dot] ac [dot] in
Research Interests:
Sequential Decision Making: Multi-armed Bandits, Reinforcement Learning
Privacy, Safety, Fairness: Differential Privacy, Algorithmic Fairness
Language Model Optimization: Alignment Algorithms, In-context Learning
About me: I am an Assistant Professor at the Department of Computer Science and Engineering, Indian Institute of Technology Kanpur. Previously, I was a Postdoctoral Researcher at Microsoft Research, India, with Dr. Nagarajan Natarajan. Before that, I was a Postdoctoral fellow at Dept. of Systems Engineering, Boston University. Before that, I did my PhD from the ECE Dept. of the Indian Institute of Science, Bangalore, where I was advised by Prof. Aditya Gopalan . I have also spent some time working at Google, USA, as a research intern. I did my masters from the Indian Institute of Science, Bangalore, and bachelor's from Jadavpur University. Here is my CV.
IITK Students interested in working with me: I am currently looking for PhD/Masters/UG students with interests in:
Privacy-Preserving Machine Learning
Sequential Decision Making under Uncertainty
Language Model Optimization
Quantum Machine Learning
Please look at my Publications to get a sense of my current research. If you are interested, feel free to send an email for further details.
Students looking for short-term (less than 3 months) projects: Unfortunately, I don't have any open positions at this moment. So, please don't send any emails regarding this. Most probably, you will not get any reply.
Updates (recent):
June 2025: I am visiting the Department of CSA, IISc Bangalore.
May 2025: I have received a gift fund from Adobe Research. As part of this collaboration, I am looking for 1 PhD student to work with me on LLM alignment.
May 2025: Paper on LLM alignment under preference drift accepted at ICML, 2025.
May 2025: Paper on sample-efficient LLM alignment accepted at ECML-PKDD, 2025.
April 2025: I have received an ANRF early career research grant. As part of this project, I am looking for 1 PhD and 1 MS student to work with me on privacy-preserving AI algorithms.
March 2025: Invited talk on LLM alignment at REACH Symposium, IIT Kanpur.
December 2024: Invited lecture series on Differential Privacy at Theory CS Winter School 2024, IISc Bangalore.
September 2024: Joined the Department of CSE, IIT Kanpur as an Assistant Professor.
September 2024: Paper on Private and Secure Deep Learning accepted at PETS, 2025.
August 2024: Invited talk on Aligning Language Models with Noisy Preferences at Adobe Research, Bangalore.
July 2024: Invited talk on Differential Privacy in Learning from Preference Data. Bangalore Crypto Day, IISc Bangalore, India.
June 2024: Invited talk on Aligning Language Models with Noisy Preferences at TrustML Young Scientists Seminar, RIKEN & University of Tokyo, Japan.
Representative Publications (see full list here):
Right Now, Wrong Then: Non-Stationary Direct Preference Optimization under Preference Drift. S. Son, W. Bankes, S.R. Chowdhury, B. Paige, I. Bogunovic. International Conference on Machine Learning (ICML), 2025. Link
Communication Efficient, Secure, and Private Multi-Party Deep Learning. Sankha Das, Sayak Ray Chowdhury, Nishanth Chandran, Divya Gupta, Rahul Sharma, Satya Lokam. Proceedings on Privacy Enhancing Technologies Symposium (PETS), 2025. Link
Provably Robust DPO: Aligning Language Models with Noisy Feedback. Sayak Ray Chowdhury, Anush Kini, Nagarajan Natarajan. International Conference on Machine Learning (ICML), 2024. Link
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
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