Mercer Features for Efficient Combinatorial Bayesian Optimization
Year: 2021
Type: conference-paper
Abstract: Bayesian optimization (BO) is an efficient framework for solving black-box optimization problems with expensive function evaluations. This paper addresses the BO problem setting for combinatorial spaces (e.g., sequences and graphs) that occurs naturally in science and engineering applications. A prototypical example is molecular optimization guided by expensive experiments. The key challenge is to balance the complexity of statistical models and tractability of search to select combinatorial structures for evaluation. In this paper, we propose an efficient approach referred as Mercer Features for Combinatorial Bayesian Optimization (MerCBO). The key idea behind MerCBO is to provide explicit feature maps for diffusion kernels over discrete objects by exploiting the structure of their combinatorial graph representation. These Mercer features combined with Thompson sampling as the acquisition function allows us to employ efficient solvers for finding the next structure for evaluation. Experimental evaluation on diverse real-world benchmarks demonstrates that MerCBO performs similarly or better than prior methods.
Institution: Washington State University
Language: English
Field: Decision Sciences
Domain: Social Sciences
Open Access status: diamond
Funder: National Science Foundation
Awards: OAC Core: Small: Sust-CI: A Machine Learning based Approach to Make Advanced Cyberinfrastructure Applications More Efficient and Sustainable, Collaborative Research: CNS Core: Medium: Exploiting Synergies Between Machine-Learning Algorithms and Hardware Heterogeneity for High-Performance and Reliable Manycore Computing, CAREER: Search-Based Optimization of Combinatorial Structures via Expensive Experiments
OpenAlex ID: W3116332055
