Salvato in:
Dettagli Bibliografici
Autori principali: Palmer, Aaron, Chi, Zhiyi, Aguiar, Derek, Bi, Jinbo
Natura: Preprint
Pubblicazione: 2022
Soggetti:
Accesso online:https://arxiv.org/abs/2210.06546
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909541482889216
author Palmer, Aaron
Chi, Zhiyi
Aguiar, Derek
Bi, Jinbo
author_facet Palmer, Aaron
Chi, Zhiyi
Aguiar, Derek
Bi, Jinbo
contents We develop a new type of generative autoencoder called the Goodness-of-Fit Autoencoder (GoFAE), which incorporates GoF tests at two levels. At the minibatch level, it uses GoF test statistics as regularization objectives. At a more global level, it selects a regularization coefficient based on higher criticism, i.e., a test on the uniformity of the local GoF p-values. We justify the use of GoF tests by providing a relaxed $L_2$-Wasserstein bound on the distance between the latent distribution and a distribution class. We prove that optimization based on these tests can be done with stochastic gradient descent on a compact Riemannian manifold. Empirically, we show that our higher criticism parameter selection procedure balances reconstruction and generation using mutual information and uniformity of p-values respectively. Finally, we show that GoFAE achieves comparable FID scores and mean squared errors with competing deep generative models while retaining statistical indistinguishability from Gaussian in the latent space based on a variety of hypothesis tests.
format Preprint
id arxiv_https___arxiv_org_abs_2210_06546
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle Auto-Encoding Goodness of Fit
Palmer, Aaron
Chi, Zhiyi
Aguiar, Derek
Bi, Jinbo
Machine Learning
We develop a new type of generative autoencoder called the Goodness-of-Fit Autoencoder (GoFAE), which incorporates GoF tests at two levels. At the minibatch level, it uses GoF test statistics as regularization objectives. At a more global level, it selects a regularization coefficient based on higher criticism, i.e., a test on the uniformity of the local GoF p-values. We justify the use of GoF tests by providing a relaxed $L_2$-Wasserstein bound on the distance between the latent distribution and a distribution class. We prove that optimization based on these tests can be done with stochastic gradient descent on a compact Riemannian manifold. Empirically, we show that our higher criticism parameter selection procedure balances reconstruction and generation using mutual information and uniformity of p-values respectively. Finally, we show that GoFAE achieves comparable FID scores and mean squared errors with competing deep generative models while retaining statistical indistinguishability from Gaussian in the latent space based on a variety of hypothesis tests.
title Auto-Encoding Goodness of Fit
topic Machine Learning
url https://arxiv.org/abs/2210.06546