Fast Randomized Singular Value Thresholding for Low-Rank Optimization
Abstract

Rank minimization problem can be boiled down to a tractable surrogate problem, such as Nuclear Norm Minimization (NNM), Weighted NNM (WNNM) problem. The problems related to NNM (or WNNM) can be solved iteratively by applying a closed-form proximal operator, called Singular Value Thresholding (SVT) (or Weighted SVT), but they suffer from high computational cost to compute a Singular Value Decomposition (SVD) at each iteration. In this paper, we propose an accurate and fast approximation method for SVT, called fast randomized SVT (FRSVT), where we avoid direct computation of SVD. The key idea is to extract an approximate basis for the range of a matrix from its compressed matrix. Given the basis, we compute the partial singular values of the original matrix from a small factored matrix. While the basis approximation is the bottleneck, our method is already severalfold faster than thin SVD. By adopting a range propagation technique, we can further avoid one of the bottleneck at each iteration. Our theoretical analysis provides a stepping stone between the approximation bound of SVD and its effect to NNM via SVT. Along with the analysis, our empirical results on both quantitative and qualitative studies show our approximation rarely harms the convergence behavior of the host algorithms. We apply it and validate the efficiency of our method on various vision problems, e.g. subspace clustering, weather artifact removal, simultaneous multi-image alignment and rectification.

Publications

Paper

 

Presentation

CVPR 2015 [Poster] [Slides]

 

Source Code

[Matlab code & mex code]

 

Citation

[1] Tae-Hyun Oh, Yasuyuki Matsushita, Yu-Wing Tai, In So Kweon, Fast Randomized Singular Value Thresholding for Nuclear Norm Minimization, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Jun. 2015. (28.4% acceptance rate)

[2] Tae-Hyun Oh, Yasuyuki Matsushita, Yu-Wing Tai, In So Kweon, Fast Randomized Singular Value Thresholding for Low-rank Optimization, IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), Vol. 40 (2), p.376 - 391, 2018.

 

Award

Received Gold Prize (1st place, Accept rate 0.8%), 21th HumanTech Paper Award, Samsung.

Multimedia Supplementary Material

 

© 2015 by TAE-HYUN OH. Proudly created with Wix.com

  • facebook-square
This site was designed with the
.com
website builder. Create your website today.
Start Now