Diversity By Design: Leveraging Distribution Matching for Offline Model-Based Optimization
This addresses the need for diverse optimal designs in scientific domains, though it is incremental as it builds on existing optimization methods.
The paper tackles the problem of generating diverse yet high-quality design candidates in offline model-based optimization by proposing DynAMO, which formulates diversity as a distribution matching problem, and experiments show it significantly improves diversity while discovering high-quality candidates.
The goal of offline model-based optimization (MBO) is to propose new designs that maximize a reward function given only an offline dataset. However, an important desiderata is to also propose a diverse set of final candidates that capture many optimal and near-optimal design configurations. We propose Diversity in Adversarial Model-based Optimization (DynAMO) as a novel method to introduce design diversity as an explicit objective into any MBO problem. Our key insight is to formulate diversity as a distribution matching problem where the distribution of generated designs captures the inherent diversity contained within the offline dataset. Extensive experiments spanning multiple scientific domains show that DynAMO can be used with common optimization methods to significantly improve the diversity of proposed designs while still discovering high-quality candidates.