80
6

Effective Tensor Sketching via Sparsification

Abstract

In this paper, we investigate effective sketching schemes via sparsification for high dimensional multilinear arrays or tensors. More specifically, we propose a novel tensor sparsification algorithm that retains a subset of the entries of a tensor in a judicious way, and prove that it can attain a given level of approximation accuracy in terms of tensor spectral norm with a much smaller sample complexity when compared with existing approaches. In particular, we show that for a kkth order d××dd\times\cdots\times d cubic tensor of {\it stable rank} rsr_s, the sample size requirement for achieving a relative error ε\varepsilon is, up to a logarithmic factor, of the order rs1/2dk/2/εr_s^{1/2} d^{k/2} /\varepsilon when ε\varepsilon is relatively large, and rsd/ε2r_s d /\varepsilon^2 and essentially optimal when ε\varepsilon is sufficiently small. It is especially noteworthy that the sample size requirement for achieving a high accuracy is of an order independent of kk. To further demonstrate the utility of our techniques, we also study how higher order singular value decomposition (HOSVD) of large tensors can be efficiently approximated via sparsification.

View on arXiv
Comments on this paper

We use cookies and other tracking technologies to improve your browsing experience on our website, to show you personalized content and targeted ads, to analyze our website traffic, and to understand where our visitors are coming from. See our policy.