Spatially heterogeneous learning by a deep student machine

TL;DR

This paper uses a statistical mechanics approach to analyze deep neural networks, revealing heterogeneous learning patterns and showing that generalization ability persists even in heavily over-parameterized, deep regimes.

Contribution

It provides an exact solution in the dense limit for deep neural networks and explores the effects of network depth, over-parameterization, and data effective dimension on learning and generalization.

Findings

Learning is heterogeneous across network layers.

Generalization ability persists in deep, over-parameterized networks.

Reducing data effective dimension improves generalization.

Abstract

Deep neural networks (DNN) with a huge number of adjustable parameters remain largely black boxes. To shed light on the hidden layers of DNN, we study supervised learning by a DNN of width $N$ and depth $L$ consisting of $NL$ perceptrons with $c$ inputs by a statistical mechanics approach called the teacher-student setting. We consider an ensemble of student machines that exactly reproduce $M$ sets of $N$ dimensional input/output relations provided by a teacher machine. We show that the problem becomes exactly solvable in what we call as 'dense limit': $N \gg c \gg 1$ and $M \gg 1$ with fixed $\alpha=M/c$ using the replica method developed in (H. Yoshino, (2020)). We also study the model numerically performing simple greedy MC simulations. Simulations reveal that learning by the DNN is quite heterogeneous in the network space: configurations of the teacher and the student machines are more correlated within the layers closer to the input/output boundaries while the central region remains much less correlated due to the over-parametrization in qualitative agreement with the theoretical prediction. We evaluate the generalization-error of the DNN with various depth $L$ both theoretically and numerically. Remarkably both the theory and simulation suggest generalization-ability of the student machines, which are only weakly correlated with the teacher in the center, does not vanish even in the deep limit $L \gg 1$ where the system becomes heavily over-parametrized. We also consider the impact of effective dimension $D(\leq N)$ of data by incorporating the hidden manifold model (S. Goldt et. al., (2020)) into our model. The theory implies that the loop corrections to the dense limit become enhanced by either decreasing the width $N$ or decreasing the effective dimension $D$ of the data. Simulation suggests both lead to significant improvements in generalization-ability.