Hypersphere Optimization: Approximated Gradient-Based Binary Optimization on Smooth Manifold for Photonic Inverse Design

TL;DR

This paper introduces hypersphere optimization, a novel gradient-based method for binary photonic inverse design that operates on a high-dimensional manifold, enabling smooth design transitions and overcoming issues with sharp thresholding.

Contribution

It proposes a new manifold-based optimization technique for binary arrays in photonic design, addressing gradient vanishing problems and enabling effective binary optimization.

Findings

Smooth transition of designs on the manifold with minimal pixel flips

Overcomes vanishing gradient issues in binary optimization

Applicable to various photonic inverse design problems

Abstract

Photonic inverse design typically seeks designs parameterized by binary arrays, where the values of each element correspond to the presence or absence of material at a particular point in space. Gradient-based approaches to photonic inverse design often include thresholding of non-binary optimization arrays; when the thresholding is sufficiently sharp, binary designs are obtained. However, difficulty can arise due to vanishing gradients for sharp thresholds, which cause optimization to stall. Here, we present hypersphere optimization, a new method of carrying out binarized photonic optimization on a high dimensional manifold. We numerically show that, on the manifold, upstream gradients from the objective function can smoothly transition a design from one nearly-binary array to another with minimal pixel flips. Our method is an approximate gradient-based optimization method for binary arrays that can be applied to various photonic inverse design problems and beyond.