Diffusion Schr\"odinger Bridges with enhanced posterior sampling for metasurface inverse design

TL;DR

This paper introduces a novel generative approach based on enhanced posterior sampling within the Schr"odinger Bridge framework, enabling high-precision inverse design of large-scale metasurfaces from smaller training data.

Contribution

It develops a versatile posterior sampling method with refined training strategies, significantly improving accuracy and scalability in metasurface inverse design.

Findings

Achieves high-precision design for $350 imes 350$ pillar arrays

Trained on smaller $23 imes 23$ arrays, yet scalable to larger configurations

Demonstrates robustness and efficiency over traditional methods

Abstract

Metasurface inverse design is challenged by the intricate relationship between structural parameters and electromagnetic responses, as well as the high dimensionality of the optimization space. Local models, while commonly employed, quickly become infeasible for complex and locally coupled structures. Conventional iterative optimization techniques, on the other hand, are computationally intensive, time-consuming, and susceptible to convergence in local minima. This study explores a versatile generative methodology based on enhanced posterior sampling within the Schr\"odinger Bridge framework. By decomposing posterior sampling into amplitude and directional contributions, we effectively integrated different kind of posterior sampling. This approach is further supported by refined training strategies to enhance performance and reduce the complexity of hyperparameter optimization. The proposed framework demonstrates exceptional accuracy and robustness, representing a significant advancement in metasurface design. Notably, it enables high-precision inverse design for large-scale configurations of up to $350 \times 350$ pillar arrays, despite being trained on significantly smaller arrays of $23 \times 23$ pillars.