Nonconvex Low-Rank Tensor Completion from Noisy Data

TL;DR

This paper introduces a fast, nonconvex gradient descent algorithm for low-rank tensor completion from noisy, incomplete data, achieving near-optimal statistical guarantees and computational efficiency.

Contribution

It presents a novel two-stage nonconvex method that combines efficiency with near-optimal statistical guarantees for tensor completion.

Findings

Achieves nearly linear time tensor completion.

Provides near-optimal statistical guarantees.

Ensures minimal estimation error spread across entries.

Abstract

We study a noisy tensor completion problem of broad practical interest, namely, the reconstruction of a low-rank tensor from highly incomplete and randomly corrupted observations of its entries. While a variety of prior work has been dedicated to this problem, prior algorithms either are computationally too expensive for large-scale applications, or come with sub-optimal statistical guarantees. Focusing on "incoherent" and well-conditioned tensors of a constant CP rank, we propose a two-stage nonconvex algorithm -- (vanilla) gradient descent following a rough initialization -- that achieves the best of both worlds. Specifically, the proposed nonconvex algorithm faithfully completes the tensor and retrieves all individual tensor factors within nearly linear time, while at the same time enjoying near-optimal statistical guarantees (i.e. minimal sample complexity and optimal estimation accuracy). The estimation errors are evenly spread out across all entries, thus achieving optimal $\ell_{\infty}$ statistical accuracy. We have also discussed how to extend our approach to accommodate asymmetric tensors. The insight conveyed through our analysis of nonconvex optimization might have implications for other tensor estimation problems.