A GAN based solver of black-box inverse problems
Michael Gillhofer, Hubert Ramsauer, Johannes Brandstetter, and Sepp Hochreiter
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 results similar to those of more traditional topology optimization methods.
33rd Conference on Neural Information Processing Systems (NeurIPS 2019); e-print at openreview.net