English

An Essay on Optimization Mystery of Deep Learning

Machine Learning 2019-05-20 v1 Machine Learning

Abstract

Despite the huge empirical success of deep learning, theoretical understanding of neural networks learning process is still lacking. This is the reason, why some of its features seem "mysterious". We emphasize two mysteries of deep learning: generalization mystery, and optimization mystery. In this essay we review and draw connections between several selected works concerning the latter.

Keywords

Cite

@article{arxiv.1905.07187,
  title  = {An Essay on Optimization Mystery of Deep Learning},
  author = {Eugene Golikov},
  journal= {arXiv preprint arXiv:1905.07187},
  year   = {2019}
}