High-Dimensional Bayesian Optimization with Constraints: Application to Powder Weighing
This addresses the challenge of efficient parameter optimization in high-dimensional constrained settings, specifically for powder weighing tasks, representing an incremental improvement over existing methods.
The paper tackles the problem of Bayesian optimization failing with high-dimensional parameters under constraints, proposing a method combining parameter decomposition with disentangled representation learning to handle both equality and inequality constraints. The method reduced the number of trials by approximately 66% compared to manual tuning in a powder weighing application.
Bayesian optimization works effectively optimizing parameters in black-box problems. However, this method did not work for high-dimensional parameters in limited trials. Parameters can be efficiently explored by nonlinearly embedding them into a low-dimensional space; however, the constraints cannot be considered. We proposed combining parameter decomposition by introducing disentangled representation learning into nonlinear embedding to consider both known equality and unknown inequality constraints in high-dimensional Bayesian optimization. We applied the proposed method to a powder weighing task as a usage scenario. Based on the experimental results, the proposed method considers the constraints and contributes to reducing the number of trials by approximately 66% compared to manual parameter tuning.