HiLAB: A Hybrid Inverse-Design Framework

2025-05-23

AI Summary

Conventional topology optimization for inverse design of nanophotonic structures suffers from premature convergence to local optima, high computational cost due to full-wave electromagnetic simulations, and difficulty in simultaneously optimizing multiple objectives. Method: This paper proposes a hybrid inverse-design paradigm integrating truncated topology optimization, a Vision Transformer-based variational autoencoder (ViT-VAE), and Bayesian optimization. It jointly optimizes geometric configurations and physical hyperparameters: the ViT-VAE establishes a reusable latent space, enabling rapid task adaptation via simple acquisition function replacement; truncated adjoint optimization accelerates convergence; and randomized parameter sampling coupled with latent-space compression enhances global exploration. Contribution/Results: With over a 10× reduction in full-wave simulation count, the method successfully designs an RGB achromatic beam deflector achieving ~25% diffraction efficiency at all three target wavelengths—surpassing state-of-the-art performance.

Technology Category

• Search and Optimization: Mixed Discrete/Continuous Search
• Computer Vision: Learning & Optimization for CV
• Machine Learning: Optimization

Application Category

• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems
• Responsible Web: Algorithmic accountability and transparency on the web
• Search and Retrieval-Augmented AI: Vertical and domain-specific search

Abstract

HiLAB (Hybrid inverse-design with Latent-space learning, Adjoint-based partial optimizations, and Bayesian optimization) is a new paradigm for inverse design of nanophotonic structures. Combining early-terminated topological optimization (TO) with a Vision Transformer-based variational autoencoder (VAE) and a Bayesian search, HiLAB addresses multi-functional device design by generating diverse freeform configurations at reduced simulation costs. Shortened adjoint-driven TO runs, coupled with randomized physical parameters, produce robust initial structures. These structures are compressed into a compact latent space by the VAE, enabling Bayesian optimization to co-optimize geometry and physical hyperparameters. Crucially, the trained VAE can be reused for alternative objectives or constraints by adjusting only the acquisition function. Compared to conventional TO pipelines prone to local optima, HiLAB systematically explores near-global optima with considerably fewer electromagnetic simulations. Even after accounting for training overhead, the total number of full simulations decreases by over an order of magnitude, accelerating the discovery of fabrication-friendly devices. Demonstrating its efficacy, HiLAB is used to design an achromatic beam deflector for red, green, and blue wavelengths, achieving balanced diffraction efficiencies of ~25% while mitigating chromatic aberrations-a performance surpassing existing demonstrations. Overall, HiLAB provides a flexible platform for robust, multi-parameter photonic designs and rapid adaptation to next-generation nanophotonic challenges.

Problem

• Inverse design of nanophotonic structures with reduced simulation costs
• Multi-functional device design using diverse freeform configurations
• Overcoming local optima in conventional topological optimization pipelines

Innovation

• Hybrid inverse-design with latent-space learning
• Adjoint-based partial optimizations for robust structures
• Bayesian optimization co-optimizes geometry and hyperparameters