Anchored Scenario Coverage for Failure-Aware First-Hit Batch Inverse Design
Machine Learning
Summary
The authors address the problem of quickly finding at least one design that meets a desired target in situations where experiments often fail. They point out that simply picking the top candidates one by one can lead to repeated or wasted efforts when predictions are uncertain. To fix this, they propose a method called ARC-SC that keeps some top choices fixed and fills the rest of the batch with diverse options to cover different possibilities while managing risk. Their experiments on materials science benchmarks show that ARC-SC improves the chances of early success compared to simpler methods. Overall, the authors demonstrate a smarter way to suggest multiple designs at once to better handle uncertain and failure-prone tests.
Authors
Chuhan Yang, Chenxi Wang, Linhan Wu, Yuyang Liu
Abstract
Early discovery of at least one valid design satisfying a target requirement is a central objective in failure-prone closed-loop inverse design. A natural batch baseline ranks candidates by a product-form marginal valid-hit score, but selecting the highest-ranked candidates independently can produce redundant recommendations under predictive uncertainty and waste the experiment budget. We introduce ARC-SC(Anchored Risk-Constrained Scenario Coverage), a batch acquisition method that preserves strong marginal candidates as anchors and allocates the remaining batch positions by maximizing complementary coverage over predictive target scenarios under a risk-support constraint. In frozen-oracle closed-loop simulations on superconductivity and JARVIS materials-property benchmarks, ARC-SC yields a statistically supported improvement in first-hit discovery and remains competitive with directionally favorable first-hit performance on more challenging design space. These results establish ARC-SC as a POF-anchored, scenario-aware batch strategy for improving early valid-target discovery under structured experimental failure.