Generative Sliced MMD Flows with Riesz Kernels

arXiv2305.11463MaRDI QIDQ6510176FDOQ6510176

Authors: Johannes Hertrich, Christian Wald, Paul Hagemann 

Abstract: Maximum mean discrepancy (MMD) flows suffer from high computational costs in large scale computations. In this paper, we show that MMD flows with Riesz kernels $K(x,y)=-|x-y{|}^r$, $rin(0,2)$ have exceptional properties which allow for their efficient computation. First, the MMD of Riesz kernels coincides with the MMD of their sliced version. As a consequence, the computation of gradients of MMDs can be performed in the one-dimensional setting. Here, for $r=1$, a simple sorting algorithm can be applied to reduce the complexity from $O(MN+N^2)$ to $O((M+N)log(M+N))$ for two empirical measures with $M$ and $N$ support points. For the implementations we approximate the gradient of the sliced MMD by using only a finite number $P$ of slices. We show that the resulting error has complexity $O(sqrtd/P)$, where $d$ is the data dimension. These results enable us to train generative models by approximating MMD gradient flows by neural networks even for large scale applications. We demonstrate the efficiency of our model by image generation on MNIST, FashionMNIST and CIFAR10.

Has companion code repository: https://github.com/johertrich/sliced_mmd_flows

This page was built for publication: Generative Sliced MMD Flows with Riesz Kernels

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6510176)