BONNI: Gradient-Informed Bayesian and Interior Point Optimization for Efficient Inverse Design in Nanophotonics

2026-02-20

AI Summary

This work addresses the challenges in inverse design for nanophotonics, where global optimization suffers from slow convergence and local optimization is prone to suboptimal solutions. To overcome these limitations, the authors propose a gradient-informed Bayesian optimization framework that integrates an interior-point method with a neural network surrogate model. This approach efficiently leverages gradient information to guide sampling, achieving a balanced trade-off between global exploration and local refinement while significantly accelerating convergence. The method successfully designs a 10-layer distributed Bragg reflector with an average spectral error of only 4.5%, outperforming a previously reported 16-layer structure with 7.8% error. Its effectiveness is further validated through the design of broadband waveguide tapers and photonic crystal waveguide transition devices.

Technology Category

• Search and Optimization: Non-convex Optimization
• Machine Learning: Optimization
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization

Application Category

• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments

Abstract

Inverse design, particularly geometric shape optimization, provides a systematic approach for developing high-performance nanophotonic devices. While numerous optimization algorithms exist, previous global approaches exhibit slow convergence and conversely local search strategies frequently become trapped in local optima. To address the limitations inherent to both local and global approaches, we introduce BONNI: Bayesian optimization through neural network ensemble surrogates with interior point optimization. It augments global optimization with an efficient incorporation of gradient information to determine optimal sampling points. This capability allows BONNI to circumvent the local optima found in many nanophotonic applications, while capitalizing on the efficiency of gradient-based optimization. We demonstrate BONNI's capabilities in the design of a distributed Bragg reflector as well as a dual-layer grating coupler through an exhaustive comparison against other optimization algorithms commonly used in literature. Using BONNI, we were able to design a 10-layer distributed Bragg reflector with only 4.5% mean spectral error, compared to the previously reported results of 7.8% error with 16 layers. Further designs of a broadband waveguide taper and photonic crystal waveguide transition validate the capabilities of BONNI.

Problem

• inverse design
• nanophotonics
• optimization
• local optima
• geometric shape optimization

Innovation

• Bayesian optimization
• gradient-informed sampling
• neural network surrogate
• interior point method
• nanophotonic inverse design