Autoencoding with a Classifier System
This work addresses efficiency issues in autoencoder training for machine learning practitioners, though it is incremental as it builds on existing conditional computation and ensemble methods.
The paper tackles the problem of high computational cost and training time in large global autoencoder models by using a learning classifier system to adaptively decompose the input domain into a collection of smaller autoencoders, resulting in reduced convergence time, computational cost, and code size compared to global models.
Autoencoders are data-specific compression algorithms learned automatically from examples. The predominant approach has been to construct single large global models that cover the domain. However, training and evaluating models of increasing size comes at the price of additional time and computational cost. Conditional computation, sparsity, and model pruning techniques can reduce these costs while maintaining performance. Learning classifier systems (LCS) are a framework for adaptively subdividing input spaces into an ensemble of simpler local approximations that together cover the domain. LCS perform conditional computation through the use of a population of individual gating/guarding components, each associated with a local approximation. This article explores the use of an LCS to adaptively decompose the input domain into a collection of small autoencoders where local solutions of different complexity may emerge. In addition to benefits in convergence time and computational cost, it is shown possible to reduce code size as well as the resulting decoder computational cost when compared with the global model equivalent.