cs.CENov 16, 2026

Separating learning from search and feedback in budgeted inverse design of periodic unit cells

Authors: Shaoliang Yang, Jun Wang

Organizations: Santa Clara University, Santa Clara, CA 95053, USA

Abstract

To design a periodic material, engineers choose the shape and dimensions of a repeating cell to meet target properties. With few simulations, the benefit of a learned predictor can be hard to separate from the effect of which designs the search tries and how it uses simulator feedback. We compare two ways to predict properties in a library of 80 cell architectures, with up to 30 simulator calls per target. For each architecture, both searches use a table of predicted properties at different dimensions. One fills the table with predictions from neural networks. The other fits a simple model to the existing simulations for that architecture. Both searches use the difference between the predicted and simulated properties to adjust the next design. We generated 200 targets from simulated designs after fixing the analysis plan. The two searches showed no detectable difference in how often they matched all three properties within 2% or in the mean error of their returned designs. The upper limit of the 95% confidence interval for the gain in overall success rate was 4.5 percentage points. Follow-up controls on these targets changed success from 83.5% to 36.0% with a degraded table and 96.5% with an oracle table. In separate tests, using the simulation result to adjust the next design increased success for both types of table. Results cover one library and a coarse 32^3 voxel simulator. Designers can use this comparison to judge what a learned predictor adds when the search, feedback and budget are the same.

Figures & tables

Appendix figures & tables17 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. From Regression to Inference: Meta-Learning Predictors for Neural Architecture Search

    May 10, 2026Liping Deng, MingQing XiaoNeural Surrogate ModelingMeta-Learning

  2. Scientific feedback reveals productive regimes beyond training conventions

    Dec 12, 2025Yoon Pyo Lee, Samrendra Roy, Souvik Chakraborty +1AI for ScienceRL for Generative Models