Clarifying the theoretical boundaries of cumulative regret analysis in Gaussian process Thompson sampling — Accepted at the international conference "ICML2026".
The research paper on Bayesian optimization, involving Iwasaki from the MI-6 Corporation's research team, has been accepted at the International Conference on Machine Learning (ICML 2026). This study focuses on the theoretical performance known as "regret" of the Gaussian process Thompson sampling (GP-TS).
【Paper Information】
- Title: On Regret Bounds of Thompson Sampling for Bayesian Optimization
- Accepted Conference: Forty-Third International Conference on Machine Learning (ICML 2026)
- DOI: https://doi.org/10.48550/arXiv.2603.09276
- Authors: *Affiliations are based on information at the time of the paper's submission.*
- Shion Takeno (Nagoya University)
- Shogo Iwasaki (MI-6 Corporation)

Inquiry about this news
Contact Us OnlineMore Details & Registration
Details & Registration




