AI RESEARCH
A Finite Time Analysis of Thompson Sampling for Bayesian Optimization with Preferential Feedback
arXiv CS.LG
•
ArXi:2604.25025v1 Announce Type: cross Preference feedback, in the form of pairwise comparisons rather than scalar scores, has seen increasing use in applications such as human-, laboratory-, and expert-in-the-loop design, as well as scientific discovery. We propose a Thompson Sampling (TS) approach to Bayesian optimization with preferential feedback that models comparisons using a monotone link on latent utility differences and leverages the dueling kernel induced by a base kernel.