arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1807.01889cs.LGstat.ML
收藏

具有Kullback-Leibler和Renyi积分边界的变分自编码器的学习

Learning in Variational Autoencoders with Kullback-Leibler and Renyi Integral Bounds

Romanian Institute of Science and Technology(罗马尼亚科学与技术研究院);Max Planck Institute for Mathematics in the Sciences(马克斯·普朗克数学科学研究所)

Septimia Sârbu, Riccardo Volpi, Alexandra Peşte, Luigi Malagò

摘要:

在本文中,我们提出了两个新的界限的对数似然的基础上Kullback-Leibler和Rényi分歧,可用于变分推理,特别是变分自编码器的培训。我们的建议是出于在具有高对比度图像的连续数据集上训练VAE时遇到的困难,例如具有手写数字和字符的数据集,除非在训练期间向数据集或解码器给出的生成模型添加噪声,否则经常出现数值问题。我们提出的新的界限,这是从最大化的可能性区间的意见,允许数值稳定的训练过程,而无需添加任何额外的噪声源的数据。

英文摘要:

In this paper we propose two novel bounds for the log-likelihood based on Kullback-Leibler and the Rényi divergences, which can be used for variational inference and in particular for the training of Variational AutoEncoders. Our proposal is motivated by the difficulties encountered in training VAEs on continuous datasets with high contrast images, such as those with handwritten digits and characters, where numerical issues often appear unless noise is added, either to the dataset during training or to the generative model given by the decoder. The new bounds we propose, which are obtained from the maximization of the likelihood of an interval for the observations, allow numerically stable training procedures without the necessity of adding any extra source of noise to the data.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑