Guaranteed Nonconvex Low-Rank Tensor Estimation via Scaled Gradient Descent

TL;DR

This paper introduces a scaled gradient descent algorithm for efficient, provably convergent low-rank tensor estimation under the t-SVD framework, robust to data corruptions and applicable to various tensor problems.

Contribution

It develops the first scalable, provably convergent algorithm for low-rank tensor estimation that is independent of the tensor's condition number.

Findings

Achieves linear convergence rate independent of condition number.

Maintains low per-iteration computational cost.

Demonstrates effectiveness in accelerating tensor estimation in applications.

Abstract

Tensors, which give a faithful and effective representation to deliver the intrinsic structure of multi-dimensional data, play a crucial role in an increasing number of signal processing and machine learning problems. However, tensor data are often accompanied by arbitrary signal corruptions, including missing entries and sparse noise. A fundamental challenge is to reliably extract the meaningful information from corrupted tensor data in a statistically and computationally efficient manner. This paper develops a scaled gradient descent (ScaledGD) algorithm to directly estimate the tensor factors with tailored spectral initializations under the tensor-tensor product (t-product) and tensor singular value decomposition (t-SVD) framework. With tailored variants for tensor robust principal component analysis, (robust) tensor completion and tensor regression, we theoretically show that ScaledGD achieves linear convergence at a constant rate that is independent of the condition number of the ground truth low-rank tensor, while maintaining the low per-iteration cost of gradient descent. To the best of our knowledge, ScaledGD is the first algorithm that provably has such properties for low-rank tensor estimation with the t-SVD. Finally, numerical examples are provided to demonstrate the efficacy of ScaledGD in accelerating the convergence rate of ill-conditioned low-rank tensor estimation in a number of applications.