Fast Robust Tensor Principal Component Analysis via Fiber CUR Decomposition

HanQin Cai, Zehan Chao, Longxiu Huang, Deanna Needell; Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops, 2021, pp. 189-197

Abstract


We study the problem of tensor robust principal component analysis (TRPCA), that aims to separate an underlying low-multilinear-rank tensor and a sparse outlier tensor from their sum. In this work, we propose a fast non-convex algorithm, coined Robust Tensor CUR (RTCUR), for large-scale TRPCA problems. RTCUR considers a framework of alternating projections and utilizes the recently developed tensor Fiber CUR decomposition to dramatically lower its computational complexity. The speed advantage of RTCUR is empirically verified against the state-of-the-art on both synthetic and real-world datasets.

Related Material


[pdf] [arXiv]
[bibtex]
@InProceedings{Cai_2021_ICCV, author = {Cai, HanQin and Chao, Zehan and Huang, Longxiu and Needell, Deanna}, title = {Fast Robust Tensor Principal Component Analysis via Fiber CUR Decomposition}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2021}, pages = {189-197} }