13 papers
Randomized Kriging Believer for Parallel Bayesian Optimization with Regret Bounds
Shuhei Sugiura, Ichiro Takeuchi, Shion Takeno
We consider the optimization problem of an expensive-to-evaluate black-box function, in which we can obtain noisy function values in parallel. For this problem, parallel Bayesian o…
On Regret Bounds of Thompson Sampling for Bayesian Optimization
Shion Takeno, Shogo Iwazaki
We study a widely used Bayesian optimization method, Gaussian process Thompson sampling (GP-TS), under the assumption that the objective function is a sample path from a GP. Compar…
Optimal-Point Variance Reduction For Bayesian Optimization With Regret Guarantee
Shion Takeno
This paper studies a one-step lookahead Bayesian optimization (BO) method and its theoretical guarantee. Although the empirical effectiveness of one-step lookahead BO methods, such…
Safe Distributionally Robust Feature Selection under Covariate Shift
Hiroyuki Hanada, Satoshi Akahane, Noriaki Hashimoto +2
In practical machine learning, the environments encountered during the model development and deployment phases often differ, especially when a model is used by many users in divers…
Regret Analysis of Posterior Sampling-Based Expected Improvement for Bayesian Optimization
Shion Takeno, Yu Inatsu, Masayuki Karasuyama +1
Bayesian optimization is a powerful tool for optimizing an expensive-to-evaluate black-box function. In particular, the effectiveness of expected improvement (EI) has been demonstr…
Regret Analysis for Randomized Gaussian Process Upper Confidence Bound
Shion Takeno, Yu Inatsu, Masayuki Karasuyama
Gaussian process upper confidence bound (GP-UCB) is a theoretically established algorithm for Bayesian optimization (BO), where we assume the objective function follows a GP. O…