3 papers
cs.LG2025
Analysis of Thompson Sampling for Controlling Unknown Linear Diffusion Processes
Mohamad Kazem Shirani Faradonbeh, Sadegh Shirani, Mohsen Bayati
Linear diffusion processes serve as canonical continuous-time models for dynamic decision-making under uncertainty. These systems evolve according to drift matrices that specify th…
cs.LG2025
Geometry-Aware Approaches for Balancing Performance and Theoretical Guarantees in Linear Bandits
Yuwei Luo, Mohsen Bayati
This paper is motivated by recent research in the -dimensional stochastic linear bandit literature, which has revealed an unsettling discrepancy: algorithms like Thompson sampli…
cs.LG2024
Speed Up the Cold-Start Learning in Two-Sided Bandits with Many Arms
Mohsen Bayati, Junyu Cao, Wanning Chen
Multi-armed bandit (MAB) algorithms are efficient approaches to reduce the opportunity cost of online experimentation and are used by companies to find the best product from period…