Skip to yearly menu bar Skip to main content


Poster

Analysis of Learning a Flow-based Generative Model from Limited Sample Complexity

Hugo Cui · Florent Krzakala · Eric Vanden-Eijnden · Lenka Zdeborova

Halle B #75
[ ]
Thu 9 May 1:45 a.m. PDT — 3:45 a.m. PDT

Abstract: We study the problem of training a flow-based generative model, parametrized by a two-layer autoencoder, to sample from a high-dimensional Gaussian mixture. We provide a sharp end-to-end analysis of the problem. First, we provide a tight closed-form characterization of the learnt velocity field, when parametrized by a shallow denoising auto-encoder trained on a finite number $n$ of samples from the target distribution. Building on this analysis, we provide a sharp description of the corresponding generative flow, which pushes the base Gaussian density forward to an approximation of the target density. In particular, we provide closed-form formulae for the distance between the means of the generated mixture and the mean of the target mixture, which we show decays as $\Theta_n(\frac{1}{n})$. Finally, this rate is shown to be in fact Bayes-optimal.

Chat is not available.