paper-with-me

Papers

Convergence Analysis for Rectangular Matrix Completion Using Burer-Monteiro Factorization and Gradient Descent

2016-05-23 · Qinqing Zheng, John Lafferty

We address the rectangular matrix completion problem by lifting the unknown matrix to a positive semidefinite matrix in higher dimension, and optimizing a nonconvex objective over the semidefinite factor using a simple gradient descent scheme. With $O( \mu r^2 \kappa^2 n \max(\mu, \log n))$ random observations of a $n_1 \times n_2$ $\mu$-incoherent matrix of rank $r$ and condition number $\kappa$, where $n = \max(n_1, n_2)$, the algorithm linearly converges to the global optimum with high probability.

📄 PDF Abstract BibTeX arXiv:1605.07051

Code (0)

등록된 구현이 없습니다.

Tasks

Matrix Completion

Similar Papers 제목 키워드 기반

Conic Descent and its Application to Memory-efficient Optimization over Positive Semidefinite Matrices

2020-12-01 · NeurIPS 2020 12 · John C. Duchi, Oliver Hinder, Andrew Naber, Yinyu Ye

We present an extension of the conditional gradient method to problems whose feasible sets are convex cones. We provide a convergence analysis for the method and for variants with nonconvex objectives, and we extend the …

Matrix CompletionRetrieval

Nonconvex Rectangular Matrix Completion via Gradient Descent without $\ell_{2,\infty}$ Regularization

2019-01-18 · Ji Chen, Dekai Liu, Xiao-Dong Li

The analysis of nonconvex matrix completion has recently attracted much attention in the community of machine learning thanks to its computational convenience. Existing analysis on this problem, however, usually relies o…

Matrix Completion

Semidefinite Programming versus Burer-Monteiro Factorization for Matrix Sensing

2022-08-15 · Baturalp Yalcin, Ziye Ma, Javad Lavaei, Somayeh Sojoudi

Many fundamental low-rank optimization problems, such as matrix completion, phase synchronization/retrieval, power system state estimation, and robust PCA, can be formulated as the matrix sensing problem. Two main approa…

Matrix CompletionRetrievalState Estimation

Euclidean Distance Matrix Completion via Asymmetric Projected Gradient Descent

2025-04-28 · Yicheng Li, Xinghua Sun

This paper proposes and analyzes a gradient-type algorithm based on Burer-Monteiro factorization, called the Asymmetric Projected Gradient Descent (APGD), for reconstructing the point set configuration from partial Eucli…

LEMMAMatrix Completion

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

2026-06-30 · Yudong Wei, Liang Zhang, Bingcong Li, Niao He arxiv

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. We propose a unified framework, term…