Phalguni Nanda

Profile_Picture_Phalguni_1.JPG

Hello! Welcome to my webpage. I am a PhD student in the Edwardson School of Industrial Engineering, Purdue University, West Lafayette, where I am advised by Prof. Zaiwei Chen. My research develops rigorous non-asymptotic analyses that characterize sample complexity and learning dynamics in reinforcement learning, with the goal of designing algorithms that are practically effective and provably efficient in high-dimensional stochastic settings for sequential decision making. I also hold a MS in Mathematical Statistics from Purdue University. My CV can be found here.

Prior to Purdue, I was a Project Assistant in the Department of Mathematics of Birla Institute of Technology and Science Pilani - Hyderabad Campus, under the supervision of Prof. Gujji Murali Mohan Reddy. Earlier, I received my Bachelors and Masters degrees in Mathematics (through the Five-Year Integrated M.Sc. programme) from the National Institute of Technology Rourkela, India. During this period, I completed a summer research internship at the Applied Statistics Unit of the Indian Statistical Institute, Kolkata, working with Prof. Prajamitra Bhuyan and Prof. Anup Dewanji.

News

Jun 15, 2026 I will present a poster on our recent work Natural Policy Gradient as Doubly Smoothed Policy Iteration: A Bellman-Operator Framework at the Stochastic Networks Conference 2026.
Jun 11, 2026 I will present our paper A Minimal-Assumption Analysis of Q-Learning with Time-Varying Policies at the ACM SIGMETRICS 2026 (Best Paper Award Finalist) [arXiv]
May 17, 2026 I will present my research in the Three-Minute Thesis Pitch at the IISE Doctoral Colloquium, held as part of the IISE Annual Conference and Expo 2026 in Arlington, Texas.