Deep Generative Prior for First Order Inverse Optimization
This addresses a critical challenge in domains like semiconductor manufacturing and materials science, offering a more efficient alternative to computationally expensive generative AI and scalable but noisy Bayesian optimization methods.
The paper tackles the problem of inverse design optimization in complex systems lacking explicit mathematical representations, which prevents first-order gradient-based methods. It introduces Deep Physics Prior (DPP), a method that enables first-order inverse optimization using pretrained neural operators to enforce prior constraints, achieving robust solutions when prior distributions are unknown.
Inverse design optimization aims to infer system parameters from observed solutions, posing critical challenges across domains such as semiconductor manufacturing, structural engineering, materials science, and fluid dynamics. The lack of explicit mathematical representations in many systems complicates this process and makes the first order optimization impossible. Mainstream approaches, including generative AI and Bayesian optimization, address these challenges but have limitations. Generative AI is computationally expensive, while Bayesian optimization, relying on surrogate models, suffers from scalability, sensitivity to priors, and noise issues, often leading to suboptimal solutions. This paper introduces Deep Physics Prior (DPP), a novel method enabling first-order gradient-based inverse optimization with surrogate machine learning models. By leveraging pretrained auxiliary Neural Operators, DPP enforces prior distribution constraints to ensure robust and meaningful solutions. This approach is particularly effective when prior data and observation distributions are unknown.