Trap of Feature Diversity in the Learning of MLPs

Abstract

In this paper, we focus on a typical two-phase phenomenon in the learning of multi-layer perceptrons (MLPs), and we aim to explain the reason for the decrease of feature diversity in the first phase. Specifically, people find that, in the training of MLPs, the training loss does not decrease significantly until the second phase. To this end, we further explore the reason why the diversity of features over different samples keeps decreasing in the first phase, which hurts the optimization of MLPs. We explain such a phenomenon in terms of the learning dynamics of MLPs. Furthermore, we theoretically explain why four typical operations can alleviate the decrease of the feature diversity.

References in corpus (7)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• The Loss Surfaces of Multilayer Networks
• A Closer Look at Memorization in Deep Networks
• Regularizing CNNs with Locally Constrained Decorrelations
• The Neural Tangent Kernel in High Dimensions: Triple Descent and a Multi-Scale Theory of Generalization
• Triple descent and the two kinds of overfitting: Where & why do they appear?
• A Tail-Index Analysis of Stochastic Gradient Noise in Deep Neural Networks