Information-Theoretic Multi-Model Fusion for Target-Oriented Adaptive Sampling in Materials Design

TL;DR

This paper introduces an information-theoretic adaptive sampling framework for efficient target-oriented materials discovery, focusing on high-dimensional, heterogeneous design spaces with limited evaluation budgets.

Contribution

It presents a novel approach that combines model beliefs, priors, and multi-model fusion to improve sample efficiency and reliability in materials design tasks.

Findings

Achieves top-performing regions within 100 evaluations in diverse tasks.

Demonstrates robustness on synthetic benchmarks with rugged landscapes.

Improves sample efficiency across a wide range of design problems.

Abstract

Target-oriented discovery under limited evaluation budgets requires making reliable progress in high-dimensional, heterogeneous design spaces where each new measurement is costly, whether experimental or high-fidelity simulation. We present an information-theoretic framework for target-oriented adaptive sampling that reframes optimization as trajectory discovery: instead of approximating the full response surface, the method maintains and refines a low-entropy information state that concentrates search on target-relevant directions. The approach couples data, model beliefs, and physics/structure priors through dimension-aware information budgeting, adaptive bootstrapped distillation over a heterogeneous surrogate reservoir, and structure-aware candidate manifold analysis with Kalman-inspired multi-model fusion to balance consensus-driven exploitation and disagreement-driven exploration. Evaluated under a single unified protocol without dataset-specific tuning, the framework improves sample efficiency and reliability across 14 single- and multi-objective materials design tasks spanning candidate pools from $600$ to $4 \times 10^6$ and feature dimensions from $10$ to $10^3$, typically reaching top-performing regions within 100 evaluations. Complementary 20-dimensional synthetic benchmarks (Ackley, Rastrigin, Schwefel) further demonstrate robustness to rugged and multimodal landscapes.