> simulation by means of second-kind Galerkin boundary element method.>> Source: Elke Spindler "Second-Kind Single Trace Boundary Integral>> Formulations for Scattering at Composite Objects", ETH Diss 23620, 2016."" > > simulation by means of second-kind Galerkin boundary element method.>> Source: Elke Spindler "Second-Kind Single Trace Boundary Integral>> Formulations for Scattering at Composite Objects", ETH Diss 23620, 2016."" > Research reports – Seminar for Applied Mathematics | ETH Zurich

Research reports

Iterative Surrogate Model Optimization (ISMO): An active learning algorithm for PDE constrained optimization with deep neural networks

by K. Lye and S. Mishra and D. Ray and P. Chandrashekar

(Report number 2020-53)

Abstract
We present a novel active learning algorithm, termed a iiterative surrogate model optimization (ISMO), for robust and efficient numerical approximation of PDE constrained optimization problems. This algorithm is based on deep neural networks and its key feature is the iterative selection of training data through a feedback loop between deep neural networks and any underlying standard optimization algorithm. Under suitable hypotheses, we show that the resulting optimizers converge exponentially fast (and with exponentially decaying variance), with respect to increasing number of training samples. Numerical examples for optimal control, parameter identification and shape optimization problems for PDEs are provided to validate the proposed theory and to illustrate that ISMO significantly outperforms a standard deep neural network based surrogate optimization algorithm.

Keywords: Deep Neural Networks, Active Learning, Surrogates, PDE constrained optimization

BibTeX
@Techreport{LMRC20_926,
  author = {K. Lye and S. Mishra and D. Ray and P. Chandrashekar},
  title = {Iterative Surrogate Model Optimization (ISMO): An active learning algorithm for PDE constrained optimization with deep neural networks},
  institution = {Seminar for Applied Mathematics, ETH Z{\"u}rich},
  number = {2020-53},
  address = {Switzerland},
  url = {https://www.sam.math.ethz.ch/sam_reports/reports_final/reports2020/2020-53.pdf },
  year = {2020}
}

Disclaimer
© Copyright for documents on this server remains with the authors. Copies of these documents made by electronic or mechanical means including information storage and retrieval systems, may only be employed for personal use. The administrators respectfully request that authors inform them when any paper is published to avoid copyright infringement. Note that unauthorised copying of copyright material is illegal and may lead to prosecution. Neither the administrators nor the Seminar for Applied Mathematics (SAM) accept any liability in this respect. The most recent version of a SAM report may differ in formatting and style from published journal version. Do reference the published version if possible (see SAM Publications).

JavaScript has been disabled in your browser