A multi-source extension of constrained Max-value Entropy Search for Bayesian optimization incorporates auxiliary data sources to improve early exploration and performance under constraints even with weak correlations.
Increasing the Scope as You Learn: Adaptive Bayesian Optimization in Nested Subspaces
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
abstract
Recent advances have extended the scope of Bayesian optimization (BO) to expensive-to-evaluate black-box functions with dozens of dimensions, aspiring to unlock impactful applications, for example, in the life sciences, neural architecture search, and robotics. However, a closer examination reveals that the state-of-the-art methods for high-dimensional Bayesian optimization (HDBO) suffer from degrading performance as the number of dimensions increases or even risk failure if certain unverifiable assumptions are not met. This paper proposes BAxUS that leverages a novel family of nested random subspaces to adapt the space it optimizes over to the problem. This ensures high performance while removing the risk of failure, which we assert via theoretical guarantees. A comprehensive evaluation demonstrates that BAxUS achieves better results than the state-of-the-art methods for a broad set of applications.
fields
cs.LG 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Recasts sampling-based nonconvex optimization as smoothed gradient descent to obtain non-asymptotic convergence guarantees and introduces the DIDA annealed algorithm that converges to the global optimum.
citing papers explorer
-
Constrained Bayesian Optimisation with Multiple Information Sources
A multi-source extension of constrained Max-value Entropy Search for Bayesian optimization incorporates auxiliary data sources to improve early exploration and performance under constraints even with weak correlations.
-
Global Convergence of Sampling-Based Nonconvex Optimization through Diffusion-Style Smoothing
Recasts sampling-based nonconvex optimization as smoothed gradient descent to obtain non-asymptotic convergence guarantees and introduces the DIDA annealed algorithm that converges to the global optimum.