Principal Bit Analysis: Autoencoding with Schur-Concave Loss

Jayadev Acharya, Sourbh Bhadane, Aaron B. Wagner

Publication date: 5 June 2021

Abstract: We consider a linear autoencoder in which the latent variables are quantized, or corrupted by noise, and the constraint is Schur-concave in the set of latent variances. Although finding the optimal encoder/decoder pair for this setup is a nonconvex optimization problem, we show that decomposing the source into its principal components is optimal. If the constraint is strictly Schur-concave and the empirical covariance matrix has only simple eigenvalues, then any optimal encoder/decoder must decompose the source in this way. As one application, we consider a strictly Schur-concave constraint that estimates the number of bits needed to represent the latent variables under fixed-rate encoding, a setup that we call emph{Principal Bit Analysis (PBA)}. This yields a practical, general-purpose, fixed-rate compressor that outperforms existing algorithms. As a second application, we show that a prototypical autoencoder-based variable-rate compressor is guaranteed to decompose the source into its principal components.

Has companion code repository: https://github.com/SourbhBh/PBA

This page was built for publication: Principal Bit Analysis: Autoencoding with Schur-Concave Loss