Sparse and Low-Rank Tensor Decomposition

Part of Advances in Neural Information Processing Systems 28 (NIPS 2015)

Bibtex Metadata Paper Reviews Supplemental


Parikshit Shah, Nikhil Rao, Gongguo Tang


Motivated by the problem of robust factorization of a low-rank tensor, we study the question of sparse and low-rank tensor decomposition. We present an efficient computational algorithm that modifies Leurgans' algoirthm for tensor factorization. Our method relies on a reduction of the problem to sparse and low-rank matrix decomposition via the notion of tensor contraction. We use well-understood convex techniques for solving the reduced matrix sub-problem which then allows us to perform the full decomposition of the tensor. We delineate situations where the problem is recoverable and provide theoretical guarantees for our algorithm. We validate our algorithm with numerical experiments.