Bounce: Reliable High-Dimensional Bayesian Optimization for Combinatorial and Mixed Spaces
This addresses the need for reliable optimization in impactful applications like materials discovery and neural architecture search, representing a novel method for a known bottleneck.
The paper tackles the problem of unreliable Bayesian optimization for high-dimensional black-box functions with mixed and combinatorial inputs, proposing Bounce, which achieves and often improves upon state-of-the-art performance in comprehensive experiments.
Impactful applications such as materials discovery, hardware design, neural architecture search, or portfolio optimization require optimizing high-dimensional black-box functions with mixed and combinatorial input spaces. While Bayesian optimization has recently made significant progress in solving such problems, an in-depth analysis reveals that the current state-of-the-art methods are not reliable. Their performances degrade substantially when the unknown optima of the function do not have a certain structure. To fill the need for a reliable algorithm for combinatorial and mixed spaces, this paper proposes Bounce that relies on a novel map of various variable types into nested embeddings of increasing dimensionality. Comprehensive experiments show that Bounce reliably achieves and often even improves upon state-of-the-art performance on a variety of high-dimensional problems.