Learning Low-Dimensional Embeddings for Black-Box Optimization
This addresses efficiency issues in black-box optimization for researchers and practitioners dealing with high-dimensional problems, though it appears incremental as it builds on existing meta-learning and dimensionality reduction techniques.
The paper tackles the challenge of high-dimensional black-box optimization with limited trial budgets by proposing a meta-learning approach to pre-compute a low-dimensional manifold for a class of problems, enabling optimization in reduced space and reducing effort to find near-optimal solutions.
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.