The Difficulty of Training Deep Architectures and the Effect of Unsupervised Pre-Training
Dumitru Erhan, Pierre-Antoine Manzagol, Yoshua Bengio, Samy Bengio, Pascal Vincent; JMLR W&CP 5:153-160, 2009.
Whereas theoretical work suggests that deep architectures might be more efficient at representing highly-varying functions, training deep architectures was unsuccessful until the recent advent of algorithms based on unsupervised pretraining. Even though these new algorithms have enabled training deep models, many questions remain as to the nature of this difficult learning problem. Answering these questions is important if learning in deep architectures is to be further improved. We attempt to shed some light on these questions through extensive simulations. The experiments confirm and clarify the advantage of unsupervised pre-training. They demonstrate the robustness of the training procedure with respect to the random initialization, the positive effect of pre-training in terms of optimization and its role as a kind of regularizer. We show the influence of architecture depth, model capacity, and number of training examples.