ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2203.02790
17
23

A Robust Spectral Algorithm for Overcomplete Tensor Decomposition

5 March 2022
Samuel B. Hopkins
T. Schramm
Jonathan Shi
ArXivPDFHTML
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 000) tensors over (Rd)⊗4(\mathbb{R}^d)^{\otimes 4}(Rd)⊗4 with rank n≤d2n \le d^2n≤d2. 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)O~(n2d3)≤O~(d7), which is subquadratic in the input size d4d^4d4 (where we have suppressed factors related to the condition number of the input tensor).

View on arXiv
Comments on this paper