Complex-Valued Autoencoders

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.

Final version, journal ref added

Cited by in corpus (12)

• An empirical analysis of the optimization of deep network loss surfaces
• Characterization of Gradient Dominance and Regularity Conditions for Neural Networks
• Deep Learning without Poor Local Minima
• The Multilinear Structure of ReLU Networks
• Learning in the Machine: Random Backpropagation and the Deep Learning Channel
• Deep Neural Networks with Multi-Branch Architectures Are Less Non-Convex
• Deep linear neural networks with arbitrary loss: All local minima are global
• Analytic Network Learning
• Deep Online Convex Optimization with Gated Games
• Neural Networks with Complex-Valued Weights Have No Spurious Local Minima
• Avoiding local minima in multilayer network optimization by incremental training
• Proactive Message Passing on Memory Factor Networks