# Robust Low-rank Tensor Decomposition with the operatornameL2 Criterion

arXiv: https://arxiv.org/abs/2208.11806 · HTML: https://mlsanity.com/paper/2208.11806/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Aug 2022.

## Built on by (most cited first, 4 of 4)

- [Faster Robust Tensor Power Method for Arbitrary Order](https://mlsanity.com/paper/2306.00406/) (2023)
- [Low-Rank Robust Subspace Tensor Clustering for Metro Passenger Flow Modeling](https://mlsanity.com/paper/2404.04403/) (2024)
- [Casewise and Cellwise Robust Multilinear Principal Component Analysis](https://mlsanity.com/paper/2503.07327/) (2025)
- [A Robust and Non-Iterative Tensor Decomposition Method with Automatic Thresholding](https://mlsanity.com/paper/2505.06203/) (2025)

## Abstract (arXiv)

The growing prevalence of tensor data, or multiway arrays, in science and engineering applications motivates the need for tensor decompositions that are robust against outliers. In this paper, we present a robust Tucker decomposition estimator based on the operatornameL2 criterion, called the Tucker-operatornameL2E. Our numerical experiments demonstrate that Tucker-operatornameL2E has empirically stronger recovery performance in more challenging high-rank scenarios compared with existing alternatives. The appropriate Tucker-rank can be selected in a data-driven manner with cross-validation or hold-out validation. The practical effectiveness of Tucker-operatornameL2E is validated on real data applications in fMRI tensor denoising, PARAFAC analysis of fluorescence data, and feature extraction for classification of corrupted images.