Non-Linear Matrix Factorization with Gaussian Processes

[edit]

Neil D. Lawrence, University of Sheffield
Raquel Urtasun, University of Toronto

in Proceedings of the International Conference in Machine Learning 26

Related Material

Abstract

A popular approach to collaborative filtering is matrix factorization. In this paper we develop a non-linear probabilistic matrix factorization using Gaussian process latent variable models. We use stochastic gradient descent (SGD) to optimize the model. SGD allows us to apply Gaussian processes to data sets with millions of observations without approximate methods. We apply our approach to benchmark movie recommender data sets. The results show better than previous state-of-the-art performance.


@InProceedings{lawrence-nlmf09,
  title = 	 {Non-Linear Matrix Factorization with Gaussian Processes},
  author = 	 {Neil D. Lawrence and Raquel Urtasun},
  booktitle = 	 {Proceedings of the International Conference in Machine Learning},
  year = 	 {2009},
  editor = 	 {Leon Bottou and Michael Littman},
  volume = 	 {26},
  address = 	 {San Francisco, CA},
  month = 	 {00},
  publisher = 	 {Morgan Kauffman},
  edit = 	 {https://github.com/lawrennd//publications/edit/gh-pages/_posts/2009-01-01-lawrence-nlmf09.md},
  url =  	 {http://inverseprobability.com/publications/lawrence-nlmf09.html},
  abstract = 	 {A popular approach to collaborative filtering is matrix factorization. In this paper we develop a non-linear probabilistic matrix factorization using Gaussian process latent variable models. We use stochastic gradient descent (SGD) to optimize the model. SGD allows us to apply Gaussian processes to data sets with millions of observations without approximate methods. We apply our approach to benchmark movie recommender data sets. The results show better than previous state-of-the-art performance.},
  crossref =  {Bottou:icml09},
  key = 	 {Lawrence:nlmf09},
  linkpdf = 	 {ftp://ftp.dcs.shef.ac.uk/home/neil/collab.pdf},
  linksoftware = {https://github.com/SheffieldML/collab/},
  group = 	 {gplvm, collaborative filtering}
 

}
%T Non-Linear Matrix Factorization with Gaussian Processes
%A Neil D. Lawrence and Raquel Urtasun
%B 
%C Proceedings of the International Conference in Machine Learning
%D 
%E Leon Bottou and Michael Littman
%F lawrence-nlmf09
%I Morgan Kauffman	
%P --
%R 
%U http://inverseprobability.com/publications/lawrence-nlmf09.html
%V 26
%X A popular approach to collaborative filtering is matrix factorization. In this paper we develop a non-linear probabilistic matrix factorization using Gaussian process latent variable models. We use stochastic gradient descent (SGD) to optimize the model. SGD allows us to apply Gaussian processes to data sets with millions of observations without approximate methods. We apply our approach to benchmark movie recommender data sets. The results show better than previous state-of-the-art performance.
TY  - CPAPER
TI  - Non-Linear Matrix Factorization with Gaussian Processes
AU  - Neil D. Lawrence
AU  - Raquel Urtasun
BT  - Proceedings of the International Conference in Machine Learning
PY  - 2009/01/01
DA  - 2009/01/01
ED  - Leon Bottou
ED  - Michael Littman	
ID  - lawrence-nlmf09
PB  - Morgan Kauffman	
SP  - 
EP  - 
L1  - ftp://ftp.dcs.shef.ac.uk/home/neil/collab.pdf
UR  - http://inverseprobability.com/publications/lawrence-nlmf09.html
AB  - A popular approach to collaborative filtering is matrix factorization. In this paper we develop a non-linear probabilistic matrix factorization using Gaussian process latent variable models. We use stochastic gradient descent (SGD) to optimize the model. SGD allows us to apply Gaussian processes to data sets with millions of observations without approximate methods. We apply our approach to benchmark movie recommender data sets. The results show better than previous state-of-the-art performance.
ER  -

Lawrence, N.D. & Urtasun, R.. (2009). Non-Linear Matrix Factorization with Gaussian Processes. Proceedings of the International Conference in Machine Learning 26:-