BriefGPT.xyz
Dec, 2021
低维数据存在下的变分自编码器:优化空间及内在偏向
Variational autoencoders in the presence of low-dimensional data: landscape and implicit bias
HTML
PDF
Frederic Koehler, Viraj Mehta, Andrej Risteski, Chenghui Zhou
TL;DR
本文研究了变分自编码器的训练问题,提出了一种二阶段的训练算法,证明了该算法可以在低维流形上训练,并且得到的生成器可以恰好支持原本的低维流形,且是由于训练算法的隐式偏差而非VAE损失本身的原因。
Abstract
variational autoencoders
(VAEs) are one of the most commonly used
generative models
, particularly for image data. A prominent difficulty in training VAEs is data that is supported on a lower dimensional
→