SOURCE-LINKED INTELLIGENCE

No-Regret Bayesian Optimization with Finite-Library Input-Warped Kernels

arXiv · AI, language, vision and robotics · article · Sep 2, 2026 · UTC

Gaussian-process Bayesian optimization (GP-BO) excels at black-box optimization of costly functions, e.g., hyperparameter optimization (HPO) and multi-agent system (MAS) design. Convergence-rate guarantees exist for select methods, notably GP upper confidence bound (GP-UCB), but require a fixed kernel. Critically, the kernel encodes how input proximity affects objective value similarity. When raw coordinates poorly match this geometry - as with log-scaled hyperparameters or localized peaks - input warping can greatly improve sample efficiency, yet known GP-UCB proofs require a fixed kernel. We

Read original source ↗ Open in workspace

recordType

paper

region

Global