Principal Bit Analysis: Autoencoding with Schur-Concave Loss
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.
Cite
@article{arxiv.2106.02796,
title = {Principal Bit Analysis: Autoencoding with Schur-Concave Loss},
author = {Sourbh Bhadane and Aaron B. Wagner and Jayadev Acharya},
journal= {arXiv preprint arXiv:2106.02796},
year = {2021}
}
Comments
ICML 2021