Portfolio-Based Constrained Multi-Objective Bayesian Optimization for Materials Design
Abstract
Materials discovery and design campaigns can be formulated as constrained multi-objective Bayesian optimization (CMOBO) problems, within which each experimental decision negotiates between two coupled but competing goals: discovering feasible candidates and refining the underlying Pareto front. Here we recast acquisition-function choice as an adaptive policy-selection problem over a portfolio of conventional and feasibility-focused acquisition functions. This was done using two controllers: UCB-Bandit, a modified UCB multi-armed bandit, and Agentic-Switch, a multi-agent decision system driven by a large language model (LLM). Both were evaluated against fixed-policy baselines in silico across five synthetic benchmark functions and two materials design case studies. The adaptive policies performed competitively in terms of both cumulative feasibility count and feasible hypervolume improvement, while each individual acquisition function performed well for only one metric, suggesting that adaptive policies are better suited for constrained materials science problems.
Related
- Multi-period Value-at-Risk Constrained Portfolio Optimization via DC Programming
- Not All Objectives Are Born Equal: Priority-Constrained Descent for Hierarchical Multi-Objective Optimization
- Simple Extensions of Single-Objective Acquisition Functions and Hedge Strategies for Multi-Objective Bayesian Optimization
- Geometry-Aware Multi-Objective Optimization: Norm-Constrained Oracles with Entropic Weight Updates
- Multi-objective Bayesian optimization from a common descent direction viewpoint
BibTeX
@misc{sinha2026portfoliobased,
title = {{Portfolio-Based Constrained Multi-Objective Bayesian Optimization for Materials Design}},
author = {Sushant Sinha and Christofer Hardcastle and Robert Robinson and Shakti Prasad Padhy and Brent Vela and Douglas Allaire and Raymundo Arroyave},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.19550},
eprint = {2609.19550},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.19550},
}
RIS
TY - UNPB
TI - Portfolio-Based Constrained Multi-Objective Bayesian Optimization for Materials Design
AU - Sushant Sinha
AU - Christofer Hardcastle
AU - Robert Robinson
AU - Shakti Prasad Padhy
AU - Brent Vela
AU - Douglas Allaire
AU - Raymundo Arroyave
PY - 2026
DA - 2026/09/17
PB - arXiv
DO - 10.48550/arxiv.2609.19550
UR - https://arxiv.org/abs/2609.19550
AB - Materials discovery and design campaigns can be formulated as constrained multi-objective Bayesian optimization (CMOBO) problems, within which each experimental decision negotiates between two coupled but competing goals: discovering feasible candidates and refining the underlying Pareto front. Here we recast acquisition-function choice as an adaptive policy-selection problem over a portfolio of conventional and feasibility-focused acquisition functions. This was done using two controllers: UCB-Bandit, a modified UCB multi-armed bandit, and Agentic-Switch, a multi-agent decision system driven by a large language model (LLM). Both were evaluated against fixed-policy baselines in silico across five synthetic benchmark functions and two materials design case studies. The adaptive policies performed competitively in terms of both cumulative feasibility count and feasible hypervolume improvement, while each individual acquisition function performed well for only one metric, suggesting that adaptive policies are better suited for constrained materials science problems.
ER -