A directional Gaussian smoothing optimization method for computational inverse design in nanophotonics

TL;DR

This paper introduces an extended directional Gaussian smoothing (DGS) optimization method tailored for constrained inverse design problems in nanophotonics, improving exploration and efficiency over traditional local-gradient approaches.

Contribution

The authors extend the DGS method to handle bounded and constrained optimization, incorporating adaptive strategies and a dynamic growth mechanism for better inverse design in nanophotonics.

Findings

Enhanced design performance with the DGS method in nanophotonics.

Reduced material usage while maintaining high performance.

Superior results compared to state-of-the-art approaches.

Abstract

Local-gradient-based optimization approaches lack nonlocal exploration ability required for escaping from local minima in non-convex landscapes. A directional Gaussian smoothing (DGS) approach was recently proposed by the authors (Zhang et al., 2020) and used to define a truly nonlocal gradient, referred to as the DGS gradient, in order to enable nonlocal exploration in high-dimensional black-box optimization. Promising results show that replacing the traditional local gradient with the nonlocal DGS gradient can significantly improve the performance of gradient-based methods in optimizing highly multi-modal loss functions. However, the current DGS method is designed for unbounded and unconstrained optimization problems, making it inapplicable to real-world engineering design optimization problems where the tuning parameters are often bounded and the loss function is usually constrained by physical processes. In this work, we propose to extend the DGS approach to the constrained inverse design framework in order to find a better design. The proposed framework has its advantages in portability and flexibility to naturally incorporate the parameterization, physics simulation, and objective formulation together to build up an effective inverse design workflow. A series of adaptive strategies for smoothing radius and learning rate updating are developed to improve the computational efficiency and robustness. To enable a clear binarized design, a dynamic growth mechanism is imposed on the projection strength in parameterization. Our methodology is demonstrated by an example of designing a nanoscale wavelength demultiplexer and shows superior performance compared to the state-of-the-art approaches. By incorporating volume constraints, the optimized design achieves an equivalently high performance but significantly reduces the amount of material usage.