论文标题
带有Riemannian Brownian Motion Priors的变异自动编码器
Variational Autoencoders with Riemannian Brownian Motion Priors
论文作者
论文摘要
变异自动编码器（VAE）代表低维潜在空间中给定的数据，通常假定为欧几里得。这种假设自然会导致标准高斯先前的共同选择，而不是连续的潜在变量。然而，最近的工作表明，这一先验对模型容量产生了不利影响，从而导致了低标准的性能。我们建议欧几里得假设位于这种失败模式的核心。为了解决这个问题，我们假设潜在空间上假设一个riemannian结构，该结构构成了潜在代码的原则性几何视图，并用Riemannian Brownian Motion先验代替了标准高斯先验。我们提出了一种有效的推理方案，该方案不依赖于先前的未知归一化因素。最后，我们证明了这一先验仅使用一个附加标量参数可显着提高模型能力。
Variational Autoencoders (VAEs) represent the given data in a low-dimensional latent space, which is generally assumed to be Euclidean. This assumption naturally leads to the common choice of a standard Gaussian prior over continuous latent variables. Recent work has, however, shown that this prior has a detrimental effect on model capacity, leading to subpar performance. We propose that the Euclidean assumption lies at the heart of this failure mode. To counter this, we assume a Riemannian structure over the latent space, which constitutes a more principled geometric view of the latent codes, and replace the standard Gaussian prior with a Riemannian Brownian motion prior. We propose an efficient inference scheme that does not rely on the unknown normalizing factor of this prior. Finally, we demonstrate that this prior significantly increases model capacity using only one additional scalar parameter.
