Gradient Descent on Two-layer Nets: Margin Maximization and Simplicity Bias.

Kaifeng Lyu Zhiyuan Li Runzhe Wang Sanjeev Arora

Published in: CoRR (2021)

Keyphrases

margin maximization
support vector
web image annotation
dimensionality reduction
metric learning
support vector machine
discriminative information
intra class
pairwise
machine learning
pattern recognition
high dimensional
principal component analysis
learning tasks