Monge-Amp\`ere Flow for Generative Modeling

Author name not available (Why is that?)

Publication date: 26 September 2018

Abstract: We present a deep generative model, named Monge-Amp`ere flow, which builds on continuous-time gradient flow arising from the Monge-Amp`ere equation in optimal transport theory. The generative map from the latent space to the data space follows a dynamical system, where a learnable potential function guides a compressible fluid to flow towards the target density distribution. Training of the model amounts to solving an optimal control problem. The Monge-Amp`ere flow has tractable likelihoods and supports efficient sampling and inference. One can easily impose symmetry constraints in the generative model by designing suitable scalar potential functions. We apply the approach to unsupervised density estimation of the MNIST dataset and variational calculation of the two-dimensional Ising model at the critical point. This approach brings insights and techniques from Monge-Amp`ere equation, optimal transport, and fluid dynamics into reversible flow-based generative models.

Has companion code repository: https://github.com/wangleiphy/MongeAmpereFlow

This page was built for publication: Monge-Amp\`ere Flow for Generative Modeling

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6307343)