LGMLSep 20, 2021

Computationally Efficient High-Dimensional Bayesian Optimization via Variable Selection

arXiv:2109.09264v216 citations
AI Analysis

This addresses the problem of time-consuming optimization in high-dimensional domains for researchers and practitioners using BO, representing an incremental improvement over existing embedding-based methods.

The paper tackles the challenge of scaling Bayesian Optimization (BO) to high-dimensional functions by developing a method that uses variable selection to automatically learn axis-aligned sub-spaces without pre-specified hyperparameters, achieving computational efficiency as shown in empirical tests on synthetic and real problems.

Bayesian Optimization (BO) is a method for globally optimizing black-box functions. While BO has been successfully applied to many scenarios, developing effective BO algorithms that scale to functions with high-dimensional domains is still a challenge. Optimizing such functions by vanilla BO is extremely time-consuming. Alternative strategies for high-dimensional BO that are based on the idea of embedding the high-dimensional space to the one with low dimension are sensitive to the choice of the embedding dimension, which needs to be pre-specified. We develop a new computationally efficient high-dimensional BO method that exploits variable selection. Our method is able to automatically learn axis-aligned sub-spaces, i.e. spaces containing selected variables, without the demand of any pre-specified hyperparameters. We theoretically analyze the computational complexity of our algorithm and derive the regret bound. We empirically show the efficacy of our method on several synthetic and real problems.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes