Tackling Multimodal Device Distributions in Inverse Photonic Design using Invertible Neural Networks

TL;DR

This paper demonstrates how invertible neural networks can effectively model the full distribution of solutions in multimodal inverse photonic design problems, outperforming traditional methods like cVAE.

Contribution

It introduces a conditional invertible neural network approach to accurately capture multimodal solution distributions in inverse design tasks, improving over existing methods.

Findings

cINN accurately models multimodal distributions

cINN outperforms cVAE in flexibility and accuracy

Method applied successfully to nanophotonic device design

Abstract

Inverse design, the process of matching a device or process parameters to exhibit a desired performance, is applied in many disciplines ranging from material design over chemical processes and to engineering. Machine learning has emerged as a promising approach to overcome current limitations imposed by the dimensionality of the parameter space and multimodal parameter distributions. Most traditional optimization routines assume an invertible one-to-one mapping between the design parameters and the target performance. However, comparable or even identical performance may be realized by different designs, yielding a multimodal distribution of possible solutions to the inverse design problem which confuses the optimization algorithm. Here, we show how a generative modeling approach based on invertible neural networks can provide the full distribution of possible solutions to the inverse design problem and resolve the ambiguity of nanodevice inverse design problems featuring multimodal distributions. We implement a Conditional Invertible Neural Network (cINN) and apply it to a proof-of-principle nanophotonic problem, consisting in tailoring the transmission spectrum of a metallic film milled by subwavelength indentations. We compare our approach with the commonly used conditional Variational Autoencoder (cVAE) framework and show the superior flexibility and accuracy of the proposed cINNs when dealing with multimodal device distributions. Our work shows that invertible neural networks provide a valuable and versatile toolkit for advancing inverse design in nanoscience and nanotechnology.