中文
相关论文

相关论文: Exact Linear Convergence Rate Analysis for Low-Ran…

200 篇论文

Optimization problems with rank constraints arise in many applications, including matrix regression, structured PCA, matrix completion and matrix decomposition problems. An attractive heuristic for solving such problems is to factorize the…

统计理论 · 数学 2015-09-11 Yudong Chen , Martin J. Wainwright

Gradient descent dynamics on the deep matrix factorization problem is extensively studied as a simplified theoretical model for deep neural networks. Although the convergence theory for two-layer matrix factorization is well-established, no…

最优化与控制 · 数学 2025-11-20 Minrui Luo , Weihang Xu , Xiang Gao , Maryam Fazel , Simon Shaolei Du

This paper investigates the asymmetric low-rank matrix completion problem, which can be formulated as an unconstrained non-convex optimization problem with a nonlinear least-squares objective function, and is solved via gradient descent…

机器学习 · 计算机科学 2025-08-14 Xu Zhang , Shuo Chen , Jinsheng Li , Xiangying Pang , Maoguo Gong

We study the asymmetric low-rank factorization problem: \[\min_{\mathbf{U} \in \mathbb{R}^{m \times d}, \mathbf{V} \in \mathbb{R}^{n \times d}} \frac{1}{2}\|\mathbf{U}\mathbf{V}^\top -\mathbf{\Sigma}\|_F^2\] where $\mathbf{\Sigma}$ is a…

最优化与控制 · 数学 2021-06-29 Tian Ye , Simon S. Du

Most existing methodologies of estimating low-rank matrices rely on Burer-Monteiro factorization, but these approaches can suffer from slow convergence, especially when dealing with solutions characterized by a large condition number,…

最优化与控制 · 数学 2024-03-06 Teng Zhang , Xing Fan

Stochastic gradient descent (SGD) on a low-rank factorization is commonly employed to speed up matrix problems including matrix completion, subspace tracking, and SDP relaxation. In this paper, we exhibit a step size scheme for SGD on a…

机器学习 · 计算机科学 2015-02-11 Christopher De Sa , Kunle Olukotun , Christopher Ré

Low-rank matrix estimation plays a central role in various applications across science and engineering. Recently, nonconvex formulations based on matrix factorization are provably solved by simple gradient descent algorithms with strong…

信号处理 · 电气工程与系统科学 2021-04-07 Cong Ma , Yuanxin Li , Yuejie Chi

While there has been a significant amount of work studying gradient descent techniques for non-convex optimization problems over the last few years, all existing results establish either local convergence with good rates or global…

数值分析 · 数学 2017-03-10 Prateek Jain , Chi Jin , Sham M. Kakade , Praneeth Netrapalli

We present theoretical results on the convergence of \emph{non-convex} accelerated gradient descent in matrix factorization models with $\ell_2$-norm loss. The purpose of this work is to study the effects of acceleration in non-convex…

We study the convergence properties of gradient descent for training deep linear neural networks, i.e., deep matrix factorizations, by extending a previous analysis for the related gradient flow. We show that under suitable conditions on…

机器学习 · 计算机科学 2021-11-25 Gabin Maxime Nguegnang , Holger Rauhut , Ulrich Terstiege

We study the convergence rate of gradient-based local search methods for solving low-rank matrix recovery problems with general objectives in both symmetric and asymmetric cases, under the assumption of the restricted isometry property.…

最优化与控制 · 数学 2022-03-10 Yingjie Bi , Haixiang Zhang , Javad Lavaei

We study the asymmetric matrix factorization problem under a natural nonconvex formulation with arbitrary overparametrization. The model-free setting is considered, with minimal assumption on the rank or singular values of the observed…

机器学习 · 计算机科学 2023-08-22 Liwei Jiang , Yudong Chen , Lijun Ding

Low-rank matrix estimation is a canonical problem that finds numerous applications in signal processing, machine learning and imaging science. A popular approach in practice is to factorize the matrix into two compact low-rank factors, and…

机器学习 · 计算机科学 2021-06-16 Tian Tong , Cong Ma , Yuejie Chi

Matrix completion has attracted much interest in the past decade in machine learning and computer vision. For low-rank promotion in matrix completion, the nuclear norm penalty is convenient due to its convexity but has a bias problem.…

机器学习 · 计算机科学 2019-03-05 Fei Wen , Rendong Ying , Peilin Liu , Trieu-Kien Truong

We study the minimization of a convex function $f(X)$ over the set of $n\times n$ positive semi-definite matrices, but when the problem is recast as $\min_U g(U) := f(UU^\top)$, with $U \in \mathbb{R}^{n \times r}$ and $r \leq n$. We study…

机器学习 · 统计学 2016-04-19 Srinadh Bhojanapalli , Anastasios Kyrillidis , Sujay Sanghavi

Matrix factorization is a popular approach for large-scale matrix completion. The optimization formulation based on matrix factorization can be solved very efficiently by standard algorithms in practice. However, due to the non-convexity…

机器学习 · 计算机科学 2016-11-18 Ruoyu Sun , Zhi-Quan Luo

In practical instances of nonconvex matrix factorization, the rank of the true solution $r^{\star}$ is often unknown, so the rank $r$ of the model can be overspecified as $r>r^{\star}$. This over-parameterized regime of matrix factorization…

最优化与控制 · 数学 2025-04-15 Gavin Zhang , Salar Fattahi , Richard Y. Zhang

We consider alternating gradient descent (AGD) with fixed step size applied to the asymmetric matrix factorization objective. We show that, for a rank-$r$ matrix $\mathbf{A} \in \mathbb{R}^{m \times n}$, $T = C…

机器学习 · 计算机科学 2024-02-09 Rachel Ward , Tamara G. Kolda

Many problems encountered in science and engineering can be formulated as estimating a low-rank object (e.g., matrices and tensors) from incomplete, and possibly corrupted, linear measurements. Through the lens of matrix and tensor…

机器学习 · 计算机科学 2023-10-11 Cong Ma , Xingyu Xu , Tian Tong , Yuejie Chi

We study the convergence of a variant of distributed gradient descent (DGD) on a distributed low-rank matrix approximation problem wherein some optimization variables are used for consensus (as in classical DGD) and some optimization…

最优化与控制 · 数学 2018-12-27 Zhihui Zhu , Qiuwei Li , Xinshuo Yang , Gongguo Tang , Michael B. Wakin
‹ 上一页 1 2 3 10 下一页 ›