Understanding Deep Learning via Decision Boundary

Abstract

This paper discovers that the neural network with lower decision boundary (DB) variability has better generalizability. Two new notions, algorithm DB variability and $(\epsilon ,\eta )$-data DB variability, are proposed to measure the decision boundary variability from the algorithm and data perspectives. Extensive experiments show significant negative correlations between the decision boundary variability and the generalizability. From the theoretical view, two lower bounds based on algorithm DB variability are proposed and do not explicitly depend on the sample size. We also prove an upper bound of order $\mathcal{O}\left(\frac{1}{\sqrt{m}}+\epsilon +\eta \log \frac{1}{\eta }\right)$ based on data DB variability. The bound is convenient to estimate without the requirement of labels, and does not explicitly depend on the network size which is usually prohibitively large in deep learning.

Accepted by IEEE TNNLS

References in corpus (10)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Prevalence of Neural Collapse during the terminal phase of deep learning training
• How to Escape Saddle Points Efficiently
• SGD on Neural Networks Learns Functions of Increasing Complexity
• Critical Points of Neural Networks: Analytical Forms and Landscape Properties
• Understanding the Decision Boundary of Deep Neural Networks: An Empirical Study
• Recent advances in deep learning theory
• Assessing Generalization of SGD via Disagreement
• Bayesian Model Selection, the Marginal Likelihood, and Generalization
• The Local Elasticity of Neural Networks

Cited by in corpus (1)

• Loss Landscape Topology Reveals Why Simple Baselines are Competitive at 3D Point Cloud Segmentation Under Class Imbalance