Improving the Generation of VAEs with High Dimensional Latent Spaces by the use of Hyperspherical Coordinates
This addresses a specific issue in generative modeling for researchers, but it is incremental as it builds on existing VAE frameworks.
The paper tackles the problem of poor generation quality in VAEs with high-dimensional latent spaces by proposing a hyperspherical coordinate parameterization, which reduces latent sparsity and improves generation ability.
Variational autoencoders (VAE) encode data into lower-dimensional latent vectors before decoding those vectors back to data. Once trained, decoding a random latent vector from the prior usually does not produce meaningful data, at least when the latent space has more than a dozen dimensions. In this paper, we investigate this issue by drawing insight from high dimensional statistics: in these regimes, the latent vectors of a standard VAE are by construction distributed uniformly on a hypersphere. We propose to formulate the latent variables of a VAE using hyperspherical coordinates, which allows compressing the latent vectors towards an island on the hypersphere, thereby reducing the latent sparsity and we show that this improves the generation ability of the VAE. We propose a new parameterization of the latent space with limited computational overhead.