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

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.

arXiv comment31 pages, 19 figures. This paper has been published in Materials & Design, 2021; 197:109213

References in corpus (16)

• Practical Bayesian Optimization of Machine Learning Algorithms
• Review article: Linear optical quantum computing
• Outlook for inverse design in nanophotonics
• A Literature Survey of Benchmark Functions For Global Optimization Problems
• Inverse design and demonstration of a compact and broadband on-chip wavelength demultiplexer
• Evolution Strategies as a Scalable Alternative to Reinforcement Learning
• Metasurface interferometry towards quantum sensors
• Adjoint method and inverse design for nonlinear nanophotonic devices
• Inverse design in photonics by topology optimization: tutorial
• Inverse-designed photonic circuits for fully passive, bias-free Kerr-based nonreciprocal transmission and routing
• Inverse design of photonic crystals through automatic differentiation
• Simulator-based training of generative models for the inverse design of metasurfaces
• Benchmarking five global optimization approaches for nano-optical shape optimization and parameter reconstruction
• Forward-Mode Differentiation of Maxwell's Equations
• Compact 200 line MATLAB code for inverse design in photonics by topology optimization: tutorial
• Computational Bounds For Photonic Design

Cited by in corpus (5)

• Physical Computing for Materials Acceleration Platforms
• Thermodynamic Consistent Neural Networks for Learning Material Interfacial Mechanics
• A Scalable Gradient-Free Method for Bayesian Experimental Design with Implicit Models
• Model Calibration of the Liquid Mercury Spallation Target using Evolutionary Neural Networks and Sparse Polynomial Expansions
• A Hybrid Gradient Method to Designing Bayesian Experiments for Implicit Models