Erratum: SGDQN Is Less Careful than Expected

Abstract

The SGD-QN algorithm described in Bordes et al. (2009) contains a subtle flaw that prevents it from reaching its design goals. Yet the flawed SGD-QN algorithm has worked well enough to be a winner of the first Pascal Large Scale Learning Challenge (Sonnenburg et al., 2008). This document clarifies the situation, proposes a corrected algorithm, and evaluates its performance.

Cite

Text

Bordes et al. "Erratum: SGDQN Is Less Careful than Expected." Journal of Machine Learning Research, 2010.

Markdown

[Bordes et al. "Erratum: SGDQN Is Less Careful than Expected." Journal of Machine Learning Research, 2010.](https://mlanthology.org/jmlr/2010/bordes2010jmlr-erratum/)

BibTeX

@article{bordes2010jmlr-erratum,
  title     = {{Erratum: SGDQN Is Less Careful than Expected}},
  author    = {Bordes, Antoine and Bottou, Léon and Gallinari, Patrick and Chang, Jonathan and Smith, S. Alex},
  journal   = {Journal of Machine Learning Research},
  year      = {2010},
  pages     = {2229-2240},
  volume    = {11},
  url       = {https://mlanthology.org/jmlr/2010/bordes2010jmlr-erratum/}
}