Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Zhang, Mingtian, Bird, Thomas, Habib, Raza, Xu, Tianlin, Barber, David
Format: Preprint
Veröffentlicht: 2019
Schlagworte:
Online-Zugang:https://arxiv.org/abs/1907.11891
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866910744012914688
author Zhang, Mingtian
Bird, Thomas
Habib, Raza
Xu, Tianlin
Barber, David
author_facet Zhang, Mingtian
Bird, Thomas
Habib, Raza
Xu, Tianlin
Barber, David
contents Probabilistic models are often trained by maximum likelihood, which corresponds to minimizing a specific f-divergence between the model and data distribution. In light of recent successes in training Generative Adversarial Networks, alternative non-likelihood training criteria have been proposed. Whilst not necessarily statistically efficient, these alternatives may better match user requirements such as sharp image generation. A general variational method for training probabilistic latent variable models using maximum likelihood is well established; however, how to train latent variable models using other f-divergences is comparatively unknown. We discuss a variational approach that, when combined with the recently introduced Spread Divergence, can be applied to train a large class of latent variable models using any f-divergence.
format Preprint
id arxiv_https___arxiv_org_abs_1907_11891
institution arXiv
publishDate 2019
record_format arxiv
spellingShingle Variational f-divergence Minimization
Zhang, Mingtian
Bird, Thomas
Habib, Raza
Xu, Tianlin
Barber, David
Machine Learning
Probabilistic models are often trained by maximum likelihood, which corresponds to minimizing a specific f-divergence between the model and data distribution. In light of recent successes in training Generative Adversarial Networks, alternative non-likelihood training criteria have been proposed. Whilst not necessarily statistically efficient, these alternatives may better match user requirements such as sharp image generation. A general variational method for training probabilistic latent variable models using maximum likelihood is well established; however, how to train latent variable models using other f-divergences is comparatively unknown. We discuss a variational approach that, when combined with the recently introduced Spread Divergence, can be applied to train a large class of latent variable models using any f-divergence.
title Variational f-divergence Minimization
topic Machine Learning
url https://arxiv.org/abs/1907.11891