A GAN based solver of black-box inverse problems

Michael Gillhofer; Hubert Ramsauer; Johannes Brandstetter; Bernhard Schäfl; Sepp Hochreiter

A GAN based solver of black-box inverse problems

Michael Gillhofer
, Hubert Ramsauer
, Johannes Brandstetter
, Bernhard Schäfl
, Sepp Hochreiter

Research output: Chapter in Book/Report/Conference proceeding › Conference proceedings › peer-review

Abstract

We propose a GAN based approach to solve inverse problems which have non-differentiable or even black-box forward relations. The idea is to find solutions via an adversarial game where the generator has to propose new samples and the discriminator has to assess the quality of the samples with respect to the forward relation $f$. However, instead of attempting to approximate $f$ directly, the discriminator only has to solve a binary classification task in local regions populated by the generated samples. We demonstrate the efficacy of our approach by applying it to an artificially generated topology optimization problem. We show that our method leads to similar results like more traditional topology optimization methods.

Original language	English
Title of host publication	Neural Information Processing Systems Foundation (NeurIPS 2019), 2019
Number of pages	1
Publication status	Published - 2019

Fields of science

305907 Medical statistics
202017 Embedded systems
202036 Sensor systems
101004 Biomathematics
101014 Numerical mathematics
101015 Operations research
101016 Optimisation
101017 Game theory
101018 Statistics
101019 Stochastics
101024 Probability theory
101026 Time series analysis
101027 Dynamical systems
101028 Mathematical modelling
101029 Mathematical statistics
101031 Approximation theory
102 Computer Sciences
102001 Artificial intelligence
102003 Image processing
102004 Bioinformatics
102013 Human-computer interaction
102018 Artificial neural networks
102019 Machine learning
102032 Computational intelligence
102033 Data mining
305901 Computer-aided diagnosis and therapy
305905 Medical informatics
202035 Robotics
202037 Signal processing
103029 Statistical physics
106005 Bioinformatics
106007 Biostatistics

JKU Focus areas

Digital Transformation

Cite this

@inproceedings{b9b16b4877b94a66919718055d9081c7,

title = "A GAN based solver of black-box inverse problems",

abstract = "We propose a GAN based approach to solve inverse problems which have non-differentiable or even black-box forward relations. The idea is to find solutions via an adversarial game where the generator has to propose new samples and the discriminator has to assess the quality of the samples with respect to the forward relation \$f\$. However, instead of attempting to approximate \$f\$ directly, the discriminator only has to solve a binary classification task in local regions populated by the generated samples. We demonstrate the efficacy of our approach by applying it to an artificially generated topology optimization problem. We show that our method leads to similar results like more traditional topology optimization methods.",

author = "Michael Gillhofer and Hubert Ramsauer and Johannes Brandstetter and Bernhard Sch{\"a}fl and Sepp Hochreiter",

year = "2019",

language = "English",

booktitle = "Neural Information Processing Systems Foundation (NeurIPS 2019), 2019",

}

TY - GEN

T1 - A GAN based solver of black-box inverse problems

AU - Gillhofer, Michael

AU - Ramsauer, Hubert

AU - Brandstetter, Johannes

AU - Schäfl, Bernhard

AU - Hochreiter, Sepp

PY - 2019

Y1 - 2019

N2 - We propose a GAN based approach to solve inverse problems which have non-differentiable or even black-box forward relations. The idea is to find solutions via an adversarial game where the generator has to propose new samples and the discriminator has to assess the quality of the samples with respect to the forward relation $f$. However, instead of attempting to approximate $f$ directly, the discriminator only has to solve a binary classification task in local regions populated by the generated samples. We demonstrate the efficacy of our approach by applying it to an artificially generated topology optimization problem. We show that our method leads to similar results like more traditional topology optimization methods.

AB - We propose a GAN based approach to solve inverse problems which have non-differentiable or even black-box forward relations. The idea is to find solutions via an adversarial game where the generator has to propose new samples and the discriminator has to assess the quality of the samples with respect to the forward relation $f$. However, instead of attempting to approximate $f$ directly, the discriminator only has to solve a binary classification task in local regions populated by the generated samples. We demonstrate the efficacy of our approach by applying it to an artificially generated topology optimization problem. We show that our method leads to similar results like more traditional topology optimization methods.

M3 - Conference proceedings

BT - Neural Information Processing Systems Foundation (NeurIPS 2019), 2019

ER -