Cover Image

Nonnegative Low-rank Matrix Recovery Can Have Spurious Local Minima

Fuente: arXiv

Saved in:

Bibliographic Details
Main Author:	Zhang, Richard Y.
Format:	Preprint
Published:	2025
Subjects:	Optimization and Control Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Can Learning Be Explained By Local Optimality In Robust Low-rank Matrix Recovery?
by: Ma, Jianhao, et al.
Published: (2023)

Statistically Optimal K-means Clustering via Nonnegative Low-rank Semidefinite Programming
by: Zhuang, Yubo, et al.
Published: (2023)

LoRA Training in the NTK Regime has No Spurious Local Minima
by: Jang, Uijeong, et al.
Published: (2024)

Sharp Global Guarantees for Nonconvex Low-rank Recovery in the Noisy Overparameterized Regime
by: Zhang, Richard Y.
Published: (2021)

Sharpness of Minima in Deep Matrix Factorization
by: Kamber, Anil, et al.
Published: (2025)

Guarantees of a Preconditioned Subgradient Algorithm for Overparameterized Asymmetric Low-rank Matrix Recovery
by: Giampouras, Paris, et al.
Published: (2024)

Sum-of-norms regularized Nonnegative Matrix Factorization
by: Ang, Andersen, et al.
Published: (2024)

Efficient Algorithms for Regularized Nonnegative Scale-invariant Low-rank Approximation Models
by: Cohen, Jeremy E., et al.
Published: (2024)

A Second-Order Majorant Algorithm for Nonnegative Matrix Factorization
by: Pham, Mai-Quyen, et al.
Published: (2023)

Majorization-minimization for Sparse Nonnegative Matrix Factorization with the $β$-divergence
by: Marmin, Arthur, et al.
Published: (2022)

Sparse Hyperparametric Itakura-Saito Nonnegative Matrix Factorization via Bi-Level Optimization
by: Selicato, Laura, et al.
Published: (2025)

In-depth Analysis of Low-rank Matrix Factorisation in a Federated Setting
by: Philippenko, Constantin, et al.
Published: (2024)

Robust Low-rank Tensor Train Recovery
by: Qin, Zhen, et al.
Published: (2024)

Preconditioned Gradient Descent for Over-Parameterized Nonconvex Matrix Factorization
by: Zhang, Gavin, et al.
Published: (2025)

Nonnegative Matrix Factorization in the Component-Wise L1 Norm for Sparse Data
by: Seraghiti, Giovanni, et al.
Published: (2026)

Accelerated Nonnegative Tensor Completion via Integer Programming
by: Pan, Wenhao, et al.
Published: (2022)

Hidden Minima in Two-Layer ReLU Networks
by: Arjevani, Yossi
Published: (2023)

Gradient Descent with Polyak's Momentum Finds Flatter Minima via Large Catapults
by: Phunyaphibarn, Prin, et al.
Published: (2023)

A Smoothing Newton Method for Rank-one Matrix Recovery
by: Maunu, Tyler, et al.
Published: (2025)

A Support-Set Algorithm for Optimization Problems with Nonnegative and Orthogonal Constraints
by: Wang, Lei, et al.
Published: (2025)

A Non-Monotone Line-Search Method for Minimizing Functions with Spurious Local Minima
by: Aminifard, Zohreh, et al.
Published: (2025)

Zeroth-Order Optimization Finds Flat Minima
by: Zhang, Liang, et al.
Published: (2025)

Spurious Stationarity and Hardness Results for Bregman Proximal-Type Algorithms
by: Chen, He, et al.
Published: (2024)

Efficient Duple Perturbation Robustness in Low-rank MDPs
by: Hu, Yang, et al.
Published: (2024)

Nonconvex Factorization and Manifold Formulations are Almost Equivalent in Low-rank Matrix Optimization
by: Luo, Yuetian, et al.
Published: (2021)

Fast and Accurate Estimation of Low-Rank Matrices from Noisy Measurements via Preconditioned Non-Convex Gradient Descent
by: Zhang, Gavin, et al.
Published: (2023)

Heaviside Low-Rank Support Matrix Machine
by: Xiu, Xianchao, et al.
Published: (2026)

Provably Efficient Representation Selection in Low-rank Markov Decision Processes: From Online to Offline RL
by: Zhang, Weitong, et al.
Published: (2021)

Gradient Descent Converges Linearly to Flatter Minima than Gradient Flow in Shallow Linear Networks
by: Beneventano, Pierfrancesco, et al.
Published: (2025)

From Saddle Points Toward Global Minima: A Newton-Type Method on Wasserstein Space
by: Lascu, Razvan-Andrei, et al.
Published: (2026)

Low-Rank Extragradient Method for Nonsmooth and Low-Rank Matrix Optimization Problems
by: Garber, Dan, et al.
Published: (2022)

Low-Rank Mirror-Prox for Nonsmooth and Low-Rank Matrix Optimization Problems
by: Garber, Dan, et al.
Published: (2022)

Low-Tubal-Rank Tensor Recovery via Factorized Gradient Descent
by: Liu, Zhiyu, et al.
Published: (2024)

Improved Global Guarantees for the Nonconvex Burer--Monteiro Factorization via Rank Overparameterization
by: Zhang, Richard Y.
Published: (2022)

Neural Collapse versus Low-rank Bias: Is Deep Neural Collapse Really Optimal?
by: Súkeník, Peter, et al.
Published: (2024)

Efficient Low-rank Identification via Accelerated Iteratively Reweighted Nuclear Norm Minimization
by: Wang, Hao, et al.
Published: (2024)

Randomized Algorithms for Symmetric Nonnegative Matrix Factorization
by: Hayashi, Koby, et al.
Published: (2024)

Disjunctive Branch-and-Bound for Certifiably Optimal Low-Rank Matrix Completion
by: Bertsimas, Dimitris, et al.
Published: (2023)

Zeroth-order Low-rank Hessian Estimation via Matrix Recovery
by: Wang, Tianyu, et al.
Published: (2024)

Low-Complexity Algorithm for Restless Bandits with Imperfect Observations
by: Liu, Keqin, et al.
Published: (2021)