English

Tensor Reconstruction Beyond Constant Rank

Computational Complexity 2022-09-12 v1 Data Structures and Algorithms

Abstract

We give reconstruction algorithms for subclasses of depth-3 arithmetic circuits. In particular, we obtain the first efficient algorithm for finding tensor rank, and an optimal tensor decomposition as a sum of rank-one tensors, when given black-box access to a tensor of super-constant rank. We obtain the following results: 1. A deterministic algorithm that reconstructs polynomials computed by Σ[k][d]Σ\Sigma^{[k]}\bigwedge^{[d]}\Sigma circuits in time poly(n,d,c)poly(k)kk10\mathsf{poly}(n,d,c) \cdot \mathsf{poly}(k)^{k^{k^{10}}} 2. A randomized algorithm that reconstructs polynomials computed by multilinear Σk][d]Σ\Sigma^{k]}\prod^{[d]}\Sigma circuits in time poly(n,d,c)kkkkO(k)\mathsf{poly}(n,d,c) \cdot k^{k^{k^{k^{O(k)}}}} 3. A randomized algorithm that reconstructs polynomials computed by set-multilinear Σk][d]Σ\Sigma^{k]}\prod^{[d]}\Sigma circuits in time poly(n,d,c)kkkkO(k)\mathsf{poly}(n,d,c) \cdot k^{k^{k^{k^{O(k)}}}}, where c=logqc=\log q if F=Fq\mathbb{F}=\mathbb{F}_q is a finite field, and cc equals the maximum bit complexity of any coefficient of ff if F\mathbb{F} is infinite. Prior to our work, polynomial time algorithms for the case when the rank, kk, is constant, were given by Bhargava, Saraf and Volkovich [BSV21]. Another contribution of this work is correcting an error from a paper of Karnin and Shpilka [KS09] that affected Theorem 1.6 of [BSV21]. Consequently, the results of [KS09, BSV21] continue to hold, with a slightly worse setting of parameters. For fixing the error we study the relation between syntactic and semantic ranks of ΣΠΣ\Sigma\Pi\Sigma circuits. We obtain our improvement by introducing a technique for learning rank preserving coordinate-subspaces. [KS09] and [BSV21] tried all choices of finding the "correct" coordinates, which led to having a fast growing function of kk at the exponent of nn. We find these spaces in time that is growing fast with kk, yet it is only a fixed polynomial in nn.

Keywords

Cite

@article{arxiv.2209.04177,
  title  = {Tensor Reconstruction Beyond Constant Rank},
  author = {Shir Peleg and Amir Shpilka and Ben Lee Volk},
  journal= {arXiv preprint arXiv:2209.04177},
  year   = {2022}
}

Comments

Abstract shortened to meet arXiv requirements; 59 pages

R2 v1 2026-06-28T00:59:57.239Z