中文
相关论文

相关论文: Symmetry, Saddle Points, and Global Optimization L…

200 篇论文

This paper considers general rank-constrained optimization problems that minimize a general objective function $f(X)$ over the set of rectangular $n\times m$ matrices that have rank at most $r$. To tackle the rank constraint and also to…

信息论 · 计算机科学 2021-09-07 Zhihui Zhu , Qiuwei Li , Gongguo Tang , Michael B. Wakin

In this paper we develop a new framework that captures the common landscape underlying the common non-convex low-rank matrix problems including matrix sensing, matrix completion and robust PCA. In particular, we show for all above problems…

机器学习 · 计算机科学 2017-04-04 Rong Ge , Chi Jin , Yi Zheng

This paper considers the minimization of a general objective function $f(X)$ over the set of rectangular $n\times m$ matrices that have rank at most $r$. To reduce the computational burden, we factorize the variable $X$ into a product of…

信息论 · 计算机科学 2018-07-04 Zhihui Zhu , Qiuwei Li , Gongguo Tang , Michael B. Wakin

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

Substantial progress has been made recently on developing provably accurate and efficient algorithms for low-rank matrix factorization via nonconvex optimization. While conventional wisdom often takes a dim view of nonconvex optimization…

机器学习 · 计算机科学 2019-10-23 Yuejie Chi , Yue M. Lu , Yuxin Chen

This work considers two popular minimization problems: (i) the minimization of a general convex function $f(\mathbf{X})$ with the domain being positive semi-definite matrices; (ii) the minimization of a general convex function…

信息论 · 计算机科学 2019-02-22 Qiuwei Li , Zhihui Zhu , Gongguo Tang

Low-rank matrix recovery is a fundamental problem in signal processing and machine learning. A recent very popular approach to recovering a low-rank matrix X is to factorize it as a product of two smaller matrices, i.e., X = UV^T, and then…

最优化与控制 · 数学 2023-07-19 Shuang Li , Qiuwei Li , Zhihui Zhu , Gongguo Tang , Michael B. Wakin

We study nonconvex optimization landscapes for learning overcomplete representations, including learning (i) sparsely used overcomplete dictionaries and (ii) convolutional dictionaries, where these unsupervised learning problems find many…

机器学习 · 计算机科学 2019-12-11 Qing Qu , Yuexiang Zhai , Xiao Li , Yuqian Zhang , Zhihui Zhu

We study a general matrix optimization problem with a fixed-rank positive semidefinite (PSD) constraint. We perform the Burer-Monteiro factorization and consider a particular Riemannian quotient geometry in a search space that has a total…

最优化与控制 · 数学 2022-11-30 Yuetian Luo , Nicolas Garcia Trillos

Techniques involving factorization are found in a wide range of applications and have enjoyed significant empirical success in many fields. However, common to a vast majority of these problems is the significant disadvantage that the…

数值分析 · 计算机科学 2015-06-26 Benjamin D. Haeffele , Rene Vidal

The proliferation of saddle points, rather than poor local minima, is increasingly understood to be a primary obstacle in large-scale non-convex optimization for machine learning. Variable elimination algorithms, like Variable Projection…

机器学习 · 计算机科学 2025-11-04 Min Gan , Guang-Yong Chen , Yang Yi , Lin Yang

Saddle point optimization is a critical problem employed in numerous real-world applications, including portfolio optimization, generative adversarial networks, and robotics. It has been extensively studied in cases where the objective…

机器学习 · 计算机科学 2025-03-25 Shubhankar Agarwal , Hamzah I. Khan , Sandeep P. Chinchali , David Fridovich-Keil

The orthogonal group synchronization problem, which aims to recover a set of $d \times d$ orthogonal matrices from their pairwise noisy products, plays a fundamental role in signal processing, computer vision, and network analysis. In…

最优化与控制 · 数学 2026-03-17 Shuyang Ling

A central challenge to many fields of science and engineering involves minimizing non-convex error functions over continuous, high dimensional spaces. Gradient descent or quasi-Newton methods are almost ubiquitously used to perform such…

机器学习 · 计算机科学 2014-05-29 Razvan Pascanu , Yann N. Dauphin , Surya Ganguli , Yoshua Bengio

A central challenge to many fields of science and engineering involves minimizing non-convex error functions over continuous, high dimensional spaces. Gradient descent or quasi-Newton methods are almost ubiquitously used to perform such…

机器学习 · 计算机科学 2014-06-11 Yann Dauphin , Razvan Pascanu , Caglar Gulcehre , Kyunghyun Cho , Surya Ganguli , Yoshua Bengio

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

We examine the squared error loss landscape of shallow linear neural networks. We show---with significantly milder assumptions than previous works---that the corresponding optimization problems have benign geometric properties: there are no…

机器学习 · 计算机科学 2018-11-06 Zhihui Zhu , Daniel Soudry , Yonina C. Eldar , Michael B. Wakin

In this paper, we propose and analyze zeroth-order stochastic approximation algorithms for nonconvex and convex optimization, with a focus on addressing constrained optimization, high-dimensional setting and saddle-point avoiding. To handle…

最优化与控制 · 数学 2019-01-16 Krishnakumar Balasubramanian , Saeed Ghadimi

Matrix sensing problems exhibit pervasive non-convexity, plaguing optimization with a proliferation of suboptimal spurious solutions. Avoiding convergence to these critical points poses a major challenge. This work provides new theoretical…

最优化与控制 · 数学 2024-03-12 Ziye Ma , Ying Chen , Javad Lavaei , Somayeh Sojoudi

Due to the non-convex nature of training Deep Neural Network (DNN) models, their effectiveness relies on the use of non-convex optimization heuristics. Traditional methods for training DNNs often require costly empirical methods to produce…

机器学习 · 计算机科学 2023-12-21 Tolga Ergen , Mert Pilanci
‹ 上一页 1 2 3 10 下一页 ›