Poster

Monte Carlo Tree Search based Variable Selection for High Dimensional Bayesian Optimization

Lei Song · Ke Xue · Xiaobin Huang · Chao Qian

Keywords: [ Monte Carlo Tree Search ] [ High-dimensional Optimization ] [ Black-box Optimization ] [ Bayesian optimization ] [ variable selection ]

[ Abstract ]
[ Poster [ OpenReview
 
Spotlight presentation: Lightning Talks 4A-4
Wed 7 Dec 6:30 p.m. PST — 6:45 p.m. PST

Abstract:

Bayesian optimization (BO) is a class of popular methods for expensive black-box optimization, and has been widely applied to many scenarios. However, BO suffers from the curse of dimensionality, and scaling it to high-dimensional problems is still a challenge. In this paper, we propose a variable selection method MCTS-VS based on Monte Carlo tree search (MCTS), to iteratively select and optimize a subset of variables. That is, MCTS-VS constructs a low-dimensional subspace via MCTS and optimizes in the subspace with any BO algorithm. We give a theoretical analysis of the general variable selection method to reveal how it can work. Experiments on high-dimensional synthetic functions and real-world problems (e.g., MuJoCo locomotion tasks) show that MCTS-VS equipped with a proper BO optimizer can achieve state-of-the-art performance.

Chat is not available.