Variational Diffusion Autoencoders with Random Walk Sampling

Understand

Variational autoencoders (VAEs) and generative adversarial networks (GANs) enjoy an intuitive connection to manifold learning: in training the decoder/generator is optimized to approximate a homeomorphism between the data distribution and the sampling space.

• This is a construction that strives to define the data manifold.
• A major obstacle to VAEs and GANs, however, is choosing a suitable prior that matches the data topology.
• Well-known consequences of poorly picked priors are posterior and mode collapse.