Rapid optimization in high dimensional space by deep kernel learning augmented genetic algorithms

TL;DR

This paper presents a novel framework combining Deep Kernel Learning with Genetic Algorithms to efficiently optimize high-dimensional spaces, significantly reducing computational costs in applications like molecular discovery and battery optimization.

Contribution

It introduces a hybrid DKL-GA approach that leverages GAs' generative capabilities and DKL's efficiency, enabling rapid optimization in complex high-dimensional problems.

Findings

Effective optimization of FerroSIM model demonstrated

Broad applicability to molecular discovery and battery charging

Significant reduction in computational demands

Abstract

Exploration of complex high-dimensional spaces presents significant challenges in fields such as molecular discovery, process optimization, and supply chain management. Genetic Algorithms (GAs), while offering significant power for creating new candidate spaces, often entail high computational demands due to the need for evaluation of each new proposed solution. On the other hand, Deep Kernel Learning (DKL) efficiently navigates the spaces of preselected candidate structures but lacks generative capabilities. This study introduces an approach that amalgamates the generative power of GAs to create new candidates with the efficiency of DKL-based surrogate models to rapidly ascertain the behavior of new candidate spaces. This DKL-GA framework can be further used to build Bayesian Optimization (BO) workflows. We demonstrate the effectiveness of this approach through the optimization of the FerroSIM model, showcasing its broad applicability to diverse challenges, including molecular discovery and battery charging optimization.