Skip to Main Content
Motivated by recommendation systems, we consider the problem of estimating block constant binary matrices (of size m Ã n) from sparse and noisy observations. The observations are obtained from the underlying block constant matrix after unknown row and column permutations, erasures, and errors. We derive upper and lower bounds on the achievable probability of error. For fixed erasure and error probability, we show that there exists a constant C1 such that if the cluster sizes are less than C1 ln(mn), then for any algorithm the probability of error approaches one as m, n Â¿ Â¿. On the other hand, we show that a simple polynomial time algorithm gives probability of error diminishing to zero provided the cluster sizes are greater than C2 ln(mn) for a suitable constant C2.