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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Valleti, Mani, Raghavan, Aditya, Kalinin, Sergei V.
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908677900861440
author Valleti, Mani
Raghavan, Aditya
Kalinin, Sergei V.
author_facet Valleti, Mani
Raghavan, Aditya
Kalinin, Sergei V.
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2410_03173
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Rapid optimization in high dimensional space by deep kernel learning augmented genetic algorithms
Valleti, Mani
Raghavan, Aditya
Kalinin, Sergei V.
Machine Learning
Materials Science
Computational Physics
Data Analysis, Statistics and Probability
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.
title Rapid optimization in high dimensional space by deep kernel learning augmented genetic algorithms
topic Machine Learning
Materials Science
Computational Physics
Data Analysis, Statistics and Probability
url https://arxiv.org/abs/2410.03173