中文
相关论文

相关论文: Over-parametrization via Lifting for Low-rank Matr…

200 篇论文

Low-rank matrix sensing is a fundamental yet challenging nonconvex problem whose optimization landscape typically contains numerous spurious local minima, making it difficult for gradient-based optimizers to converge to the global optimum.…

机器学习 · 计算机科学 2026-02-12 Tianqi Shen , Jinji Yang , Junze He , Kunhan Gao , Ziye Ma

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

We study a nonconvex optimization algorithmic approach to phase retrieval and the more general problem of semidefinite low-rank matrix sensing. Specifically, we analyze the nonconvex landscape of a quartic Burer-Monteiro factored…

最优化与控制 · 数学 2026-04-20 Andrew D. McRae

Recent work established that rank overparameterization eliminates spurious local minima in nonconvex low-rank matrix recovery under the restricted isometry property (RIP). But this does not fully explain the practical success of…

最优化与控制 · 数学 2025-05-07 Richard Y. Zhang

A recent line of work has shown that an overparametrized neural network can perfectly fit the training data, an otherwise often intractable nonconvex optimization problem. For (fully-connected) shallow networks, in the best case scenario,…

机器学习 · 计算机科学 2019-10-30 Armin Eftekhari , ChaeHwan Song , Volkan Cevher

The matrix low-rank approximation problem with additional convex constraints can find many applications and has been extensively studied before. However, this problem is shown to be nonconvex and NP-hard; most of the existing solutions are…

数值分析 · 计算机科学 2015-12-08 Ying Zhang

We consider minimizing a twice-differentiable, $L$-smooth, and $\mu$-strongly convex objective $\phi$ over an $n\times n$ positive semidefinite matrix $M\succeq0$, under the assumption that the minimizer $M^{\star}$ has low rank…

最优化与控制 · 数学 2025-02-04 Richard Y. Zhang

Low-rank adapters enable fine-tuning of large models with only a small number of parameters, thus reducing storage costs and minimizing the risk of catastrophic forgetting. However, they often pose optimization challenges, with poor…

机器学习 · 计算机科学 2024-12-16 Piotr Teterwak , Kate Saenko , Bryan A. Plummer , Ser-Nam Lim

We study a family of (potentially non-convex) constrained optimization problems with convex composite structure. Through a novel analysis of non-smooth geometry, we show that proximal-type algorithms applied to exact penalty formulations of…

最优化与控制 · 数学 2019-03-04 Yu Bai , John Duchi , Song Mei

Recently, the problem of local minima in very high dimensional non-convex optimization has been challenged and the problem of saddle points has been introduced. This paper introduces a dynamic type of normalization that forces the system to…

机器学习 · 计算机科学 2017-02-08 Armen Aghajanyan

This paper studies the problem of recovering a low-rank matrix from several noisy random linear measurements. We consider the setting where the rank of the ground-truth matrix is unknown a priori and use an objective function built from a…

最优化与控制 · 数学 2025-07-29 Lijun Ding , Zhen Qin , Liwei Jiang , Jinxin Zhou , Zhihui Zhu

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

Trace norm regularization is a widely used approach for learning low rank matrices. A standard optimization strategy is based on formulating the problem as one of low rank matrix factorization which, however, leads to a non-convex problem.…

机器学习 · 计算机科学 2017-08-01 Carlo Ciliberto , Dimitris Stamos , Massimiliano Pontil

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

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

We propose a general theory for studying the \xl{landscape} of nonconvex \xl{optimization} with underlying symmetric structures \tz{for a class of machine learning problems (e.g., low-rank matrix factorization, phase retrieval, and deep…

机器学习 · 计算机科学 2018-01-23 Xingguo Li , Junwei Lu , Raman Arora , Jarvis Haupt , Han Liu , Zhaoran Wang , Tuo Zhao

When solving large scale semidefinite programs that admit a low-rank solution, an efficient heuristic is the Burer-Monteiro factorization: instead of optimizing over the full matrix, one optimizes over its low-rank factors. This reduces the…

最优化与控制 · 数学 2019-11-15 Irène Waldspurger , Alden Waters

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

Motivated by the emerging role of interpolating machines in signal processing and machine learning, this work considers the computational aspects of over-parametrized matrix factorization. In this context, the optimization landscape may…

机器学习 · 计算机科学 2022-02-09 Armin Eftekhari
‹ 上一页 1 2 3 10 下一页 ›