25
23

A Robust Spectral Algorithm for Overcomplete Tensor Decomposition

Abstract

We give a spectral algorithm for decomposing overcomplete order-4 tensors, so long as their components satisfy an algebraic non-degeneracy condition that holds for nearly all (all but an algebraic set of measure 00) tensors over (Rd)4(\mathbb{R}^d)^{\otimes 4} with rank nd2n \le d^2. Our algorithm is robust to adversarial perturbations of bounded spectral norm. Our algorithm is inspired by one which uses the sum-of-squares semidefinite programming hierarchy (Ma, Shi, and Steurer STOC'16, arXiv:1610.01980), and we achieve comparable robustness and overcompleteness guarantees under similar algebraic assumptions. However, our algorithm avoids semidefinite programming and may be implemented as a series of basic linear-algebraic operations. We consequently obtain a much faster running time than semidefinite programming methods: our algorithm runs in time O~(n2d3)O~(d7)\tilde O(n^2d^3) \le \tilde O(d^7), which is subquadratic in the input size d4d^4 (where we have suppressed factors related to the condition number of the input tensor).

View on arXiv
Comments on this paper