Work

Range-aware Bayesian optimization for discovering diverse designs within target property windows

Year: 2026

Type: article

Abstract: Range-aware acquisition reframes Bayesian optimization to target a property window instead of a single optimum. This enables parallel search across multiple targets—each satisfied by a diverse set of designs to rank later by cost or robustness.

Source: Digital Discovery

DOI: 10.1039/d6dd00358c

Authors: Shengli Jiang, Jason Wu, Charles M. Schroeder, Michael A. Webb

Institution: Princeton University

Language: English

Topic: Machine Learning in Materials Science

Subfield: Materials Chemistry

Field: Materials Science

Domain: Physical Sciences

Open Access status: diamond

Funders: National Science Foundation, Princeton University

Award: Collaborative Research: DMREF: Machine Learning and Robotics for the Data-Driven Design of Protein-polymer Hybrid Materials