Near-separable Non-negative Matrix Factorization with ℓ_1- and Bregman Loss Functions

12/27/2013
by   Abhishek Kumar, et al.
0

Recently, a family of tractable NMF algorithms have been proposed under the assumption that the data matrix satisfies a separability condition Donoho & Stodden (2003); Arora et al. (2012). Geometrically, this condition reformulates the NMF problem as that of finding the extreme rays of the conical hull of a finite set of vectors. In this paper, we develop several extensions of the conical hull procedures of Kumar et al. (2013) for robust (ℓ_1) approximations and Bregman divergences. Our methods inherit all the advantages of Kumar et al. (2013) including scalability and noise-tolerance. We show that on foreground-background separation problems in computer vision, robust near-separable NMFs match the performance of Robust PCA, considered state of the art on these problems, with an order of magnitude faster training time. We also demonstrate applications in exemplar selection settings.

READ FULL TEXT
research
10/03/2012

Fast Conical Hull Algorithms for Near-separable Non-negative Matrix Factorization

The separability assumption (Donoho & Stodden, 2003; Arora et al., 2012)...
research
07/08/2015

Intersecting Faces: Non-negative Matrix Factorization With New Guarantees

Non-negative matrix factorization (NMF) is a natural model of admixture ...
research
06/28/2015

Robustness Analysis of Preconditioned Successive Projection Algorithm for General Form of Separable NMF Problem

The successive projection algorithm (SPA) has been known to work well fo...
research
09/07/2021

Refinement of Hottopixx and its Postprocessing

Hottopixx, proposed by Bittorf et al. at NIPS 2012, is an algorithm for ...
research
01/08/2014

Robust Large Scale Non-negative Matrix Factorization using Proximal Point Algorithm

A robust algorithm for non-negative matrix factorization (NMF) is presen...
research
09/21/2018

Local Computation Algorithms for the Lovász Local Lemma

We consider the task of designing Local Computation Algorithms (LCA) for...
research
07/05/2023

Selective inference for fMRI cluster-wise analysis, issues, and recommendations for template selection: A comment on Blain et al

Two permutation-based methods for simultaneous inference have recently b...

Please sign up or login with your details

Forgot password? Click here to reset