Papers › A Domain-Shrinking based Bayesian Optimization Algorithm with Order-Optimal Regret Performance

A Domain-Shrinking based Bayesian Optimization Algorithm with Order-Optimal Regret Performance

27 Oct 2020NeurIPS 2021 12arXiv:2010.13997archive 2025-07-28

Sudeep Salgia, Sattar Vakili, Qing Zhao

We consider sequential optimization of an unknown function in a reproducing kernel Hilbert space. We propose a Gaussian process-based algorithm and establish its order-optimal regret performance (up to a poly-logarithmic factor). This is the first GP-based algorithm with an order-optimal regret guarantee. The proposed algorithm is rooted in the methodology of domain shrinking realized through a sequence of tree-based region pruning and refining to concentrate queries in increasingly smaller high-performing regions of the function domain. The search for high-performing regions is localized and guided by an iterative estimation of the optimal function value to ensure both learning efficiency and computational efficiency. Compared with the prevailing GP-UCB family of algorithms, the proposed algorithm reduces computational complexity by a factor of O(T²ᵈ⁻¹) (where T is the time horizon and d the dimension of the function domain).

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

sudeepsalgia/gp_threds mentioned on GitHubMIT report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Bayesian OptimizationComputational Efficiency

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Gaussian ProcessPruning

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections