arXiv Machine Learning July 31, 2026 By Tingting Mu

Sparsity Induced Identifiability in Matrix Tri-Factorisation

Read the original on arXiv Machine Learning →

arXiv:2607. 27507v1 Announce Type: new Abstract: Matrix factorisation is a fundamental tool for exploiting low-dimensional structure in high-dimensional data, with applications such as data compression, denoising, structure discovery, interpretable representation learning, and dimensionality reduction.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

Sep 21

Nonnegative Matrix Factorization in the Component-Wise L1 Norm for Sparse Data

arXiv:2603.29715v2 Announce Type: replace Abstract: Nonnegative matrix factorization (NMF) approximates a nonnegative matrix, X, by the product of two nonnegative factors, WH, where W has r columns a...

By Giovanni Seraghiti, K\'evin Dubrulle, Arnaud Vandaele, Nicolas Gillis

efficiency safety

arXiv Computer Vision

Sep 15

Robust low-rank tensor completion via factorized weighted tensor schatten-p norm minimization

arXiv:2609.14307v1 Announce Type: new Abstract: Low-rank tensor factorization provides a flexible framework for completing multidimensional data from incomplete and corrupted observations. However, u...

By Binghao Wang, Feng Zhang, Wendong Wang, Jianjun Wang

efficiency

arXiv Machine Learning

Jul 1

Direction-Magnitude Decomposition for Low-Rank Matrix Optimization: Faster Convergence and Saddle-to-saddle Dynamics

arXiv:2606. 31390v1 Announce Type: cross Abstract: Low-rank matrix optimization is often carried out via the Burer-Monteiro (BM) formulation, but choosing the factorization rank $r$ is delicate and can substantially slow optimization.

By Yudong Wei, Liang Zhang, Bingcong Li, Niao He

arXiv Machine Learning

Aug 11

Understanding Alternating Minimization for Matrix Completion

arXiv:1312. 0925v4 Announce Type: replace Abstract: Alternating Minimization is a widely used and empirically successful heuristic for matrix completion and related low-rank optimization problems.

By Moritz Hardt

arXiv Machine Learning

Jul 23

Non--negative matrix factorization using the \textit{R} package \textsf{nnmf}

arXiv:2607. 20084v1 Announce Type: cross Abstract: Non--negative matrix factorization (NMF) has become an established dimensionality reduction technique for extracting latent structures from non--negative data and has found widespread applications in fields such as bioinformatics, text mining, image analysis, and recommender systems.

By Volkan Sevin\c{c}, Nikolas Kontemeniotis, Theodoros Perdikis, Michail Tsagris

arXiv Machine Learning

Jul 7

A Provably-Correct and Robust Convex Model for Smooth Separable NMF

arXiv:2511. 07109v2 Announce Type: replace-cross Abstract: Nonnegative matrix factorization (NMF) is a linear dimensionality reduction technique for nonnegative data, with applications such as hyperspectral unmixing and topic modeling.

By Junjun Pan, Valentin Leplat, Michael Ng, Nicolas Gillis

benchmarks

One email a morning, machine-written

Related stories

Nonnegative Matrix Factorization in the Component-Wise L1 Norm for Sparse Data

Robust low-rank tensor completion via factorized weighted tensor schatten-p norm minimization

Direction-Magnitude Decomposition for Low-Rank Matrix Optimization: Faster Convergence and Saddle-to-saddle Dynamics

Understanding Alternating Minimization for Matrix Completion

Non--negative matrix factorization using the \textit{R} package \textsf{nnmf}

A Provably-Correct and Robust Convex Model for Smooth Separable NMF