Complex-Valued Autoencoders

TL;DR

This paper analyzes complex-valued linear autoencoders, providing unified proofs for real and complex cases, revealing the error landscape's structure, and introducing convergent learning algorithms with insights into their properties.

Contribution

It extends autoencoder theory to complex fields, unifies real and complex cases, and offers new proofs, algorithms, and geometric insights into their error landscapes.

Findings

Error landscape has no local minima

Global minima linked to PCA

Multiple saddle points related to eigenvector subspaces

Abstract

Autoencoders are unsupervised machine learning circuits whose learning goal is to minimize a distortion measure between inputs and outputs. Linear autoencoders can be defined over any field and only real-valued linear autoencoder have been studied so far. Here we study complex-valued linear autoencoders where the components of the training vectors and adjustable matrices are defined over the complex field with the $L_2$ norm. We provide simpler and more general proofs that unify the real-valued and complex-valued cases, showing that in both cases the landscape of the error function is invariant under certain groups of transformations. The landscape has no local minima, a family of global minima associated with Principal Component Analysis, and many families of saddle points associated with orthogonal projections onto sub-space spanned by sub-optimal subsets of eigenvectors of the covariance matrix. The theory yields several iterative, convergent, learning algorithms, a clear understanding of the generalization properties of the trained autoencoders, and can equally be applied to the hetero-associative case when external targets are provided. Partial results on deep architecture as well as the differential geometry of autoencoders are also presented. The general framework described here is useful to classify autoencoders and identify general common properties that ought to be investigated for each class, illuminating some of the connections between information theory, unsupervised learning, clustering, Hebbian learning, and autoencoders.