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 ) tensors over with rank . 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 , which is subquadratic in the input size (where we have suppressed factors related to the condition number of the input tensor).
View on arXiv