In this work, we provide a deterministic alternative to the stochastic variational training of generative autoencoders. We refer to these new generative autoencoders as AutoEncoders within Flows (AEF), since the encoder and decoder are defined as affine layers of an overall invertible architecture. This results in a deterministic encoding of the data, as opposed to the stochastic encoding of VAEs. The paper introduces two related families of AEFs. The first family relies on a partition of the ambient space and is trained by exact maximum-likelihood. The second family exploits a deterministic expansion of the ambient space and is trained by maximizing the log-probability in this extended space. This latter case leaves complete freedom in the choice of encoder, decoder and prior architectures, making it a drop-in replacement for the training of existing VAEs and VAE-style models. We show that these AEFs can have strikingly higher performance than architecturally identical VAEs in terms of log-likelihood and sample quality, especially for low dimensional latent spaces. Importantly, we show that AEF samples are substantially sharper than VAE samples.

翻译：本文提出了一种替代生成式自编码器随机变分训练的确定性方法。我们将这类新型生成式自编码器称为流内自编码器（AEF），其编码器和解码器被定义为整体可逆架构中的仿射层。与变分自编码器（VAE）的随机编码不同，该方法可实现数据的确定性编码。论文介绍了两个相关AEF家族：第一类基于对潜空间的分割，通过精确最大似然法进行训练；第二类利用潜空间的确定性扩展，通过最大化扩展空间中的对数概率进行训练。后者赋予编码器、解码器和先验架构完全的选择自由度，可无缝替代现有VAE及类VAE模型的训练过程。实验表明，相较于架构相同的VAE，这些AEF在对数似然值和样本质量方面均表现显著提升，尤其在低维潜空间中更为突出。更重要的是，我们发现AEF生成的样本比VAE样本清晰度更高。