ML Anthology

Maximum-Margin Matrix Factorization

Nathan Srebro, Jason Rennie, Tommi S. Jaakkola
NeurIPS 2004 pp. 1329-1336
/neurips/2004/srebro2004neurips-maximummargin/

Abstract

We present a novel approach to collaborative prediction, using low-norm instead of low-rank factorizations. The approach is inspired by, and has strong connections to, large-margin linear discrimination. We show how to learn low-norm factorizations by solving a semi-definite program, and discuss generalization error bounds for them.

PDF NeurIPS Semantic Scholar

Cite

Text

Srebro et al. "Maximum-Margin Matrix Factorization." Neural Information Processing Systems, 2004.

Markdown

[Srebro et al. "Maximum-Margin Matrix Factorization." Neural Information Processing Systems, 2004.](https://mlanthology.org/neurips/2004/srebro2004neurips-maximummargin/)

BibTeX

@inproceedings{srebro2004neurips-maximummargin,
  title     = {{Maximum-Margin Matrix Factorization}},
  author    = {Srebro, Nathan and Rennie, Jason and Jaakkola, Tommi S.},
  booktitle = {Neural Information Processing Systems},
  year      = {2004},
  pages     = {1329-1336},
  url       = {https://mlanthology.org/neurips/2004/srebro2004neurips-maximummargin/}
}