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.
@article{arxiv.2505.01112,
title = {Learning Low-Dimensional Embeddings for Black-Box Optimization},
author = {Riccardo Busetto and Manas Mejari and Marco Forgione and Alberto Bemporad and Dario Piga},
journal= {arXiv preprint arXiv:2505.01112},
year = {2025}
}