Stability of matrix factorization for collaborative filtering

Abstract

We study the stability vis a vis adversarial noise of matrix factorization algorithm for matrix completion. In particular, our results include: (I) we bound the gap between the solution matrix of the factorization method and the ground truth in terms of root mean square error; (II) we treat the matrix factorization as a subspace fitting problem and analyze the difference between the solution subspace and the ground truth; (III) we analyze the prediction error of individual users based on the subspace stability. We apply these results to the problem of collaborative filtering under manipulator attack, which leads to useful insights and guidelines for collaborative filtering system design.

ICML2012

Cited by in corpus (4)

• Deep Spectrum Cartography: Completing Radio Map Tensors Using Learned Neural Models
• Practical Matrix Completion and Corruption Recovery using Proximal Alternating Robust Subspace Minimization
• Social Trust Prediction via Max-norm Constrained 1-bit Matrix Completion
• Crowdsourcing via Annotator Co-occurrence Imputation and Provable Symmetric Nonnegative Matrix Factorization