From Compression to Convection: A Latent Variable Perspective

Abstract: Latent variable models have been an integral part of probabilistic machine learning, ranging from simple mixture models to variational autoencoders to powerful diffusion probabilistic models at the center of recent media attention. Perhaps less well-appreciated is the intimate connection between latent variable models and compression, and the potential of these models for advancing natural science. I will begin by showcasing connections between variational methods and the theory and practice of neural data compression, ranging from constructing learnable codecs to …

abstract attention autoencoders center compression diffusion integral machine machine learning media part perspective simple variational autoencoders