arXiv Machine Learning July 1, 2026 By Yudong Wei, Liang Zhang, Bingcong Li, Niao He

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

Read the original on arXiv Machine Learning →

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.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

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 28

Low-Rank Dependence Decomposition via Accelerated Symmetric Non-negative Matrix Factorization

arXiv:2607. 24518v1 Announce Type: new Abstract: Symmetric non-negative matrix factorization (SymNMF) recovers latent group structure from a dependence matrix, but its dense, quadratic-memory objective has confined prior work to moderate sizes.

By Lavinia Ghita, Dhruv Desai, Jake Goldberg, Roman Yokunda Enzmann

benchmarks

arXiv Machine Learning

Jun 3

Suboptimality bounds for trace-bounded SDPs enable a faster and scalable low-rank SDP solver SDPLR+

arXiv:2406. 10407v3 Announce Type: replace-cross Abstract: Semidefinite programs (SDPs) and their solvers are powerful tools with many applications in machine learning and data science.

By Yufan Huang, David F. Gleich

arXiv Machine Learning

Jul 28

Weighted Low-Rank Matrix Approximation: Acceleration and Applications

arXiv:2109. 11057v2 Announce Type: replace-cross Abstract: Weighted low-rank matrix approximation (WLRMA) generalizes classical low-rank approximation and matrix completion by allowing arbitrary elementwise weights.

By Elena Tuzhilina, Trevor Hastie

arXiv Machine Learning

Jul 23

Stability of Low-Rank Implicit Regularization in Perturbed Deep Matrix Factorization

arXiv:2605. 28613v2 Announce Type: replace-cross Abstract: This paper studies the stability of low-rank implicit regularization in deep matrix factorization, a tractable model for understanding how gradient-based training can favor low-complexity structure.

By Jingzhe Wang, Hung-Hsu Chou

arXiv Machine Learning

Jul 31

Sparsity Induced Identifiability in Matrix Tri-Factorisation

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.

By Tingting Mu

efficiency safety

Related stories

Understanding Alternating Minimization for Matrix Completion

Low-Rank Dependence Decomposition via Accelerated Symmetric Non-negative Matrix Factorization

Suboptimality bounds for trace-bounded SDPs enable a faster and scalable low-rank SDP solver SDPLR+

Weighted Low-Rank Matrix Approximation: Acceleration and Applications

Stability of Low-Rank Implicit Regularization in Perturbed Deep Matrix Factorization

Sparsity Induced Identifiability in Matrix Tri-Factorisation