Time Trials on Second-Order and Variable-Learning-Rate Algorithms

Abstract

The performance of seven minimization algorithms are compared on five neural network problems. These include a variable-step-size algorithm, conjugate gradient, and several methods with explicit analytic or numerical approximations to the Hessian.

Cite

Text

Rohwer. "Time Trials on Second-Order and Variable-Learning-Rate Algorithms." Neural Information Processing Systems, 1990.

Markdown

[Rohwer. "Time Trials on Second-Order and Variable-Learning-Rate Algorithms." Neural Information Processing Systems, 1990.](https://mlanthology.org/neurips/1990/rohwer1990neurips-time/)

BibTeX

@inproceedings{rohwer1990neurips-time,
  title     = {{Time Trials on Second-Order and Variable-Learning-Rate Algorithms}},
  author    = {Rohwer, Richard},
  booktitle = {Neural Information Processing Systems},
  year      = {1990},
  pages     = {977-983},
  url       = {https://mlanthology.org/neurips/1990/rohwer1990neurips-time/}
}