English

A survey of deep learning optimizers -- first and second order methods

Machine Learning 2023-09-28 v2 Computer Vision and Pattern Recognition Optimization and Control

Abstract

Deep Learning optimization involves minimizing a high-dimensional loss function in the weight space which is often perceived as difficult due to its inherent difficulties such as saddle points, local minima, ill-conditioning of the Hessian and limited compute resources. In this paper, we provide a comprehensive review of 1414 standard optimization methods successfully used in deep learning research and a theoretical assessment of the difficulties in numerical optimization from the optimization literature.

Keywords

Cite

@article{arxiv.2211.15596,
  title  = {A survey of deep learning optimizers -- first and second order methods},
  author = {Rohan Kashyap},
  journal= {arXiv preprint arXiv:2211.15596},
  year   = {2023}
}
R2 v1 2026-06-28T07:15:24.199Z