We present new intuitions and theoretical assessments of the emergence of disentangled representation in variational autoencoders. Taking a rate-distortion theory perspective, we show the circumstances under which representations aligned with the underlying generative factors of variation of data emerge when optimising the modified ELBO bound in $\beta$-VAE, as training progresses. From these insights, we propose a modification to the training regime of $\beta$-VAE, that progressively increases the information capacity of the latent code during training. This modification facilitates the robust learning of disentangled representations in $\beta$-VAE, without the previous trade-off in reconstruction accuracy.

翻译：我们提出新的直觉和理论评估,说明在变异自动代数中出现分解的代表性。从率扭曲理论的角度看,我们显示了在何种情况下,随着培训进展,在优化以美元-VAE为约束的经修改的ELBO时,与数据变异的基本变异基因因素相一致的表述会出现。我们从这些观点出发,建议修改美元-Beta$-VAE的培训制度,逐步提高培训期间潜伏代码的信息能力。这一修改有助于在不考虑先前重建准确性的情况下,大力学习以$\beta$-VAE为单位的脱钩式表述。