English

A Channel Coding Perspective of Collaborative Filtering

Information Theory 2016-11-17 v1 math.IT

Abstract

We consider the problem of collaborative filtering from a channel coding perspective. We model the underlying rating matrix as a finite alphabet matrix with block constant structure. The observations are obtained from this underlying matrix through a discrete memoryless channel with a noisy part representing noisy user behavior and an erasure part representing missing data. Moreover, the clusters over which the underlying matrix is constant are {\it unknown}. We establish a sharp threshold result for this model: if the largest cluster size is smaller than C1log(mn)C_1 \log(mn) (where the rating matrix is of size m×nm \times n), then the underlying matrix cannot be recovered with any estimator, but if the smallest cluster size is larger than C2log(mn)C_2 \log(mn), then we show a polynomial time estimator with diminishing probability of error. In the case of uniform cluster size, not only the order of the threshold, but also the constant is identified.

Keywords

Cite

@article{arxiv.0908.2494,
  title  = {A Channel Coding Perspective of Collaborative Filtering},
  author = {S. T. Aditya and Onkar Dabeer and Bikash Kumar Dey},
  journal= {arXiv preprint arXiv:0908.2494},
  year   = {2016}
}

Comments

32 pages, 1 figure, Submitted to IEEE Transactions on Information Theory

R2 v1 2026-06-21T13:36:20.827Z