Approximation Algorithms for ℓ_0-Low Rank Approximation

10/30/2017
by   Karl Bringmann, et al.
0

We study the ℓ_0-Low Rank Approximation Problem, where the goal is, given an m × n matrix A, to output a rank-k matrix A' for which A'-A_0 is minimized. Here, for a matrix B, B_0 denotes the number of its non-zero entries. This NP-hard variant of low rank approximation is natural for problems with no underlying metric, and its goal is to minimize the number of disagreeing data positions. We provide approximation algorithms which significantly improve the running time and approximation factor of previous work. For k > 1, we show how to find, in poly(mn) time for every k, a rank O(k (n/k)) matrix A' for which A'-A_0 ≤ O(k^2 (n/k)) OPT. To the best of our knowledge, this is the first algorithm with provable guarantees for the ℓ_0-Low Rank Approximation Problem for k > 1, even for bicriteria algorithms. For the well-studied case when k = 1, we give a (2+ϵ)-approximation in sublinear time, which is impossible for other variants of low rank approximation such as for the Frobenius norm. We strengthen this for the well-studied case of binary matrices to obtain a (1+O(ψ))-approximation in sublinear time, where ψ = OPT/ A_0. For small ψ, our approximation factor is 1+o(1).

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset