Learning Low-Dimensional Embeddings for Black-Box Optimization

TL;DR

This paper introduces a meta-learning approach to identify low-dimensional manifolds for black-box optimization, significantly improving efficiency in high-dimensional, limited-trial scenarios.

Contribution

It proposes a novel meta-learning method to pre-compute low-dimensional embeddings tailored for specific problem classes, enhancing black-box optimization performance.

Findings

Reduces optimization effort in high-dimensional spaces.

Improves solution quality with fewer trials.

Demonstrates effectiveness on problem classes.

Abstract

When gradient-based methods are impractical, black-box optimization (BBO) provides a valuable alternative. However, BBO often struggles with high-dimensional problems and limited trial budgets. In this work, we propose a novel approach based on meta-learning to pre-compute a reduced-dimensional manifold where optimal points lie for a specific class of optimization problems. When optimizing a new problem instance sampled from the class, black-box optimization is carried out in the reduced-dimensional space, effectively reducing the effort required for finding near-optimal solutions.