Generalization Error Bounds for Collaborative Prediction with Low-Rank Matrices
Abstract
We prove generalization error bounds for predicting entries in a partially observed matrix by fitting the observed entries with a low-rank matrix. In justifying the analysis approach we take to obtain the bounds, we present an example of a class of functions of finite pseudodimension such that the sums of functions from this class have unbounded pseudodimension.
Cite
Text
Srebro et al. "Generalization Error Bounds for Collaborative Prediction with Low-Rank Matrices." Neural Information Processing Systems, 2004.Markdown
[Srebro et al. "Generalization Error Bounds for Collaborative Prediction with Low-Rank Matrices." Neural Information Processing Systems, 2004.](https://mlanthology.org/neurips/2004/srebro2004neurips-generalization/)BibTeX
@inproceedings{srebro2004neurips-generalization,
title = {{Generalization Error Bounds for Collaborative Prediction with Low-Rank Matrices}},
author = {Srebro, Nathan and Alon, Noga and Jaakkola, Tommi S.},
booktitle = {Neural Information Processing Systems},
year = {2004},
pages = {1321-1328},
url = {https://mlanthology.org/neurips/2004/srebro2004neurips-generalization/}
}