Deep surrogate langevin sampling for multi-objective constraint black box optimization with applications to optimal inverse design problems

Abstract

Run a computerized numerical partial differential equation solver on at least one partial differential equation representing at least one physical constraint of a physical system, to generate a training data set. A true potential corresponds to an exact solution to the at least one partial differential equation. Using a computerized machine learning system, learn, from the training data set, a surrogate of a gradient of the true potential. Using the computerized machine learning system, apply Langevin sampling to the learned surrogate of the gradient, to obtain a plurality of samples corresponding to candidate designs for the physical system. Make the plurality of samples available to a fabrication entity.