Variational autoencoders (VAEs) are one class of generative probabilistic latent-variable models designed for inference based on known data. They balance reconstruction and regularizer terms. A variational approximation produces an evidence lower bound (ELBO). Multiplying the regularizer term by beta provides a beta-VAE/ELBO, improving disentanglement of the latent space. However, any beta value different than unity violates the laws of conditional probability. To provide a similarly-parameterized VAE, we develop a Renyi (versus Shannon) entropy VAE, and a variational approximation RELBO that introduces a similar parameter. The Renyi VAE has an additional Renyi regularizer-like term with a conditional distribution that is not learned. The term is evaluated essentially analytically using a Singular Value Decomposition method.

通过在已知数据上进行推理的一类生成概率潜变量模型，变分自编码器（VAEs）通过平衡重建和正则化项。乘以beta的正则化项产生一个beta-VAE/ELBO，提高了潜空间的解缠性。然而，任何与1不同的beta值违反了条件概率的定律。为了提供一个类似参数的VAE，我们开发了一种Renyi（相对于Shannon）熵VAE以及引入类似参数的变分近似RELBO。Renyi VAE具有额外的Renyi正则化项，其条件分布不是可学习的，这个项基本上通过奇异值分解方法进行了解析评估。

重置一个已损坏的固定ELBO