Sayak Ray Chowdhury
Scholar

Sayak Ray Chowdhury

Google Scholar ID: Q0_CaxYAAAAJ
Assistant Professor of Computer Science and Engineering, Indian Institute of Technology, Kanpur
Machine LearningMulti-armed BanditsReinforcement LearningDifferential Privacy
Citations & Impact
All-time
Citations
1,162
 
H-index
15
 
i10-index
17
 
Publications
20
 
Co-authors
42
list available
Resume (English only)
Academic Achievements
  • 2025: Selected as a Young Associate of the Indian National Academy of Engineering; Received a gift fund from Adobe Research to conduct research on LLM alignment; Paper on LLM alignment under preference drift accepted at ICML, 2025; Paper on sample-efficient LLM alignment accepted at ECML-PKDD, 2025; Received an ANRF early-career research grant; Paper on communication efficient, secure, and private multi-party deep learning accepted at PETS, 2025; Paper on provably robust DPO: aligning language models with noisy feedback accepted at ICML, 2024; Paper on differentially private federated linear contextual bandits accepted at ICLR, 2024; Paper on differentially private reward estimation with preference feedback accepted at AISTATS, 2024.
Research Experience
  • Postdoctoral Researcher at Microsoft Research with Dr. Nagarajan Natarajan; Postdoctoral fellow at the Department of Systems Engineering, Boston University; Research Intern at Google.
Education
  • Ph.D. from the ECE Department of the Indian Institute of Science, Bangalore, advised by Prof. Aditya Gopalan; Master's from the Indian Institute of Science, Bangalore; Bachelor's from Jadavpur University.
Background
  • Research Interests: Sequential Decision Making, Privacy, Safety, Fairness, Language Model Optimization; Brief Introduction: Currently an Assistant Professor in the Department of Computer Science and Engineering, Indian Institute of Technology Kanpur.
Miscellany
  • Interests include Privacy-Preserving Machine Learning, Sequential Decision Making under Uncertainty, Language Model Optimization, Quantum Machine Learning.