3 papers
stat.ML2025
Preference-centric Bandits: Optimality of Mixtures and Regret-efficient Algorithms
Meltem Tatlı, Arpan Mukherjee, Prashanth L. A. +2
The objective of canonical multi-armed bandits is to identify and repeatedly select an arm with the largest reward, often in the form of the expected value of the arm's probability…
stat.ML2025
Risk-sensitive Bandits: Arm Mixture Optimality and Regret-efficient Algorithms
Meltem Tatlı, Arpan Mukherjee, Prashanth L. A. +2
This paper introduces a general framework for risk-sensitive bandits that integrates the notions of risk-sensitive objectives by adopting a rich class of distortion riskmetrics. Th…
cs.LG2024
Combinatorial Multi-armed Bandits: Arm Selection via Group Testing
Arpan Mukherjee, Shashanka Ubaru, Keerthiram Murugesan +2
This paper considers the problem of combinatorial multi-armed bandits with semi-bandit feedback and a cardinality constraint on the super-arm size. Existing algorithms for solving…