Saved in:
Bibliographic Details
Main Authors: Bardou, Anthony, Thiran, Patrick
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2505.13012
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912660434452480
author Bardou, Anthony
Thiran, Patrick
author_facet Bardou, Anthony
Thiran, Patrick
contents Time-Varying Bayesian Optimization (TVBO) is the go-to framework for optimizing a time-varying black-box objective function that may be noisy and expensive to evaluate, but its excellent empirical performance remains to be understood theoretically. Is it possible for the instantaneous regret of a TVBO algorithm to vanish asymptotically, and if so, when? We answer this question of great importance by providing upper bounds and algorithm-independent lower bounds for the cumulative regret of TVBO algorithms. In doing so, we provide important insights about the TVBO framework and derive sufficient conditions for a TVBO algorithm to have the no-regret property. To the best of our knowledge, our analysis is the first to cover all major classes of stationary kernel functions used in practice.
format Preprint
id arxiv_https___arxiv_org_abs_2505_13012
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Asymptotic Performance of Time-Varying Bayesian Optimization
Bardou, Anthony
Thiran, Patrick
Machine Learning
Time-Varying Bayesian Optimization (TVBO) is the go-to framework for optimizing a time-varying black-box objective function that may be noisy and expensive to evaluate, but its excellent empirical performance remains to be understood theoretically. Is it possible for the instantaneous regret of a TVBO algorithm to vanish asymptotically, and if so, when? We answer this question of great importance by providing upper bounds and algorithm-independent lower bounds for the cumulative regret of TVBO algorithms. In doing so, we provide important insights about the TVBO framework and derive sufficient conditions for a TVBO algorithm to have the no-regret property. To the best of our knowledge, our analysis is the first to cover all major classes of stationary kernel functions used in practice.
title Asymptotic Performance of Time-Varying Bayesian Optimization
topic Machine Learning
url https://arxiv.org/abs/2505.13012