Arpan Mukherjee
Arpan Mukherjee is an Informed AI Hub postdoctoral research associate at Imperial College London. He obtained his Ph.D. degree at the Department of Electrical, Computer and Systems Engineering (ECSE) at Rensselaer Polytechnic Institute (RPI), NY in 2024, where he was a recipient of the B. J. Baliga Fellowship. Prior to joining RPI, Arpan obtained his M. Tech degree from the Department of Electronics and Electrical Communication Engineering at IIT Kharagpur in 2019.
Arpan is broadly interested in problems at the intersection of signal processing, statistics, and machine learning. His specific interests include sequential decision-making paradigms such as bandits and reinforcement learning. Currently, his focus is on exploring the theoretical underpinnings of foundation models.
Research
Arpan is broadly interested in problems at the intersection of signal processing, statistics, and machine learning. His specific interests include sequential decision-making paradigms such as bandits and reinforcement learning. Currently, his focus is on exploring the theoretical underpinnings of foundation models.
Selected works
-
Risk-sensitive Bandits: Arm Mixture Optimality and Regret-efficient Algorithms (AISTATS 2025)
-
Best Arm Identification in Stochastic Bandits: Beyond β−optimality (Transactions on Information Theory, accepted for publication, 2024)
-
Mean-based best arm identification in stochastic bandits under reward contamination (NeurIPS 2021)