Kapilan Balagopalan

PhD Student, University of Arizona

kapilanbgp [AT] arizona.edu

Bio

I am a PhD student in Computer Science at the University of Arizona, where I’m advised by Kwang-Sung Jun. My research focuses on sequential decision-making including bandit algorithms, partial monitoring games, and reinforcement learning with applications in fine-tuning and improving large language models and recommender systems. I hold a B.Sc. in Electronics and Telecommunication Engineering from the University of Moratuwa. During my undergraduate studies, I completed a summer internship at Nanyang Technological University under the supervision of Guohua Wang where I worked on blind channel equalization in the presence of co-channel interference.

Publications

Most recent publications on Google Scholar.
‡ indicates equal contribution.

Published

Fixing the Loose Brake: Exponential-Tailed Stopping Time in Best Arm Identification

Kapilan Balagopalan‡, Tuan Ngo Nguyen‡, Yao Zhao‡, Kwang-Sung Jun

ICML'25: International Conference on Machine Learning. 2025.

Paper Code

Minimum Empirical Divergence for Sub-Gaussian Linear Bandits

Kapilan Balagopalan, Kwang-Sung Jun

AISTATS'25: International Conference on Artificial Intelligence and Statistics. 2025.

Paper Code

Blind Equalization in the Presence of Co-channel Interference Based on Higher-Order Statistics

Guohua Wang, Kapilan Balagopalan, Sirajudeen Gulam Razul, Shang-Kee Ting, Chong Meng Samson See

Circuits, Systems, and Signal Processing. 2018.

Paper
Under review

Fixed Budget is No Harder Than Fixed Confidence in Best-Arm Identification up to Logarithmic Factors

Kapilan Balagopalan‡, Yinan Li‡, Yao Zhao, Tuan Ngo Nguyen, Anton Daitche, Houssam Nassif, Kwang-Sung Jun

(under review) ICML'26: International Conference on Machine Learning. 2026.

Paper

Vitæ

Full Resume in PDF.

I made this webpage using Martin Saveski's template, available here.
Kapilan Balagopalan
kapilanbgp [AT] arizona.edu