One-shot Learning of Surrogates in PDE-constrained Optimization Under Uncertainty

Authors Philipp A. Guth, Claudia Schillings, Simon Weissmann

Publication date 21 December 2021

PDEs in connection with control and optimization (35Q93) PDEs with randomness, stochastic partial differential equations (35R60) Discrete approximations in optimal control (49M25) Computational methods for stochastic equations (aspects of stochastic analysis) (60H35)

Abstract: We propose a general framework for machine learning based optimization under uncertainty. Our approach replaces the complex forward model by a surrogate, e.g., a neural network, which is learned simultaneously in a one-shot sense when solving the optimal control problem. Our approach relies on a reformulation of the problem as a penalized empirical risk minimization problem for which we provide a consistency analysis in terms of large data and increasing penalty parameter. To solve the resulting problem, we suggest a stochastic gradient method with adaptive control of the penalty parameter and prove convergence under suitable assumptions on the surrogate model. Numerical experiments illustrate the results for linear and nonlinear surrogate models.

This page was built for publication: One-shot Learning of Surrogates in PDE-constrained Optimization Under Uncertainty

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6386298)