On the Implicit Bias in Deep-Learning Algorithms

Gal Vardi

On the Implicit Bias in Deep-Learning Algorithms

Machine Learning 2022-11-08 v3 Machine Learning

Authors: Gal Vardi

Abstract

Gradient-based deep-learning algorithms exhibit remarkable performance in practice, but it is not well-understood why they are able to generalize despite having more parameters than training examples. It is believed that implicit bias is a key factor in their ability to generalize, and hence it was widely studied in recent years. In this short survey, we explain the notion of implicit bias, review main results and discuss their implications.

Keywords

generalization in machine learning machine learning theory deep neural networks

Cite

@article{arxiv.2208.12591,
  title  = {On the Implicit Bias in Deep-Learning Algorithms},
  author = {Gal Vardi},
  journal= {arXiv preprint arXiv:2208.12591},
  year   = {2022}
}

Comments

Some minor edits

Related papers

View all related →