Work

Learning low-dimensional embeddings for black-box optimization

Year: 2026

Type: article

Abstract: Black-box optimization (BBO) is a valuable alternative to gradient-based methods when differentiating the objective function is not feasible. However, BBO often struggles with high-dimensional decision spaces and limited evaluation budgets. In this work, we propose a meta-learning approach that pre-computes a reduced-dimensional manifold capturing the optimal solutions of a class of optimization problems. For new problem instances drawn from the same class, BBO is then performed in the latent space, substantially reducing the computational effort required to reach near-optimal solutions. We further establish probabilistic upper bounds on the performance gap between solving the original problem and its reduced-dimensional counterpart. The effectiveness of the method is demonstrated both on benchmark optimization problems and on the automatic tuning of model predictive controllers.

Source: Automatica

DOI: 10.1016/j.automatica.2026.113325

Authors: Riccardo Busetto, Manas Mejari, Marco Forgione, Alberto Bemporad, Dario Piga

Institutions: Dalle Molle Institute for Artificial Intelligence Research, IMT School for Advanced Studies Lucca

Language: English

Topic: Advanced Multi-Objective Optimization Algorithms

Subfield: Computational Theory and Mathematics

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

Estimated APC paid: $3,760

Funders: European Research Council, Eurostars