中文
相关论文

相关论文: Escaping Saddle Points via Curvature-Calibrated Pe…

200 篇论文

In this paper, we give a sharp analysis for Stochastic Gradient Descent (SGD) and prove that SGD is able to efficiently escape from saddle points and find an $(\epsilon, O(\epsilon^{0.5}))$-approximate second-order stationary point in…

最优化与控制 · 数学 2019-06-05 Cong Fang , Zhouchen Lin , Tong Zhang

Escaping saddle points is a central research topic in nonconvex optimization. In this paper, we propose a simple gradient-based algorithm such that for a smooth function $f\colon\mathbb{R}^n\to\mathbb{R}$, it outputs an…

最优化与控制 · 数学 2021-11-30 Chenyi Zhang , Tongyang Li

Stochastically controlled stochastic gradient (SCSG) methods have been proved to converge efficiently to first-order stationary points which, however, can be saddle points in nonconvex optimization. It has been observed that a stochastic…

最优化与控制 · 数学 2021-04-26 Guannan Liang , Qianqian Tong , Chunjiang Zhu , Jinbo Bi

This paper shows that a perturbed form of gradient descent converges to a second-order stationary point in a number iterations which depends only poly-logarithmically on dimension (i.e., it is almost "dimension-free"). The convergence rate…

机器学习 · 计算机科学 2017-03-03 Chi Jin , Rong Ge , Praneeth Netrapalli , Sham M. Kakade , Michael I. Jordan

We analyze stochastic gradient algorithms for optimizing nonconvex problems. In particular, our goal is to find local minima (second-order stationary points) instead of just finding first-order stationary points which may be some bad…

机器学习 · 计算机科学 2019-06-24 Zhize Li

In this paper, we provide some analysis on the asymptotic escape of strict saddles in manifold optimization using the projected gradient descent (PGD) algorithm. One of our main contributions is that we extend the current analysis to…

最优化与控制 · 数学 2020-06-30 Thomas Y. Hou , Zhenzhen Li , Ziyun Zhang

In this paper, we propose a variant of Riemannian stochastic recursive gradient method that can achieve second-order convergence guarantee and escape saddle points using simple perturbation. The idea is to perturb the iterates when gradient…

最优化与控制 · 数学 2020-10-30 Andi Han , Junbin Gao

We investigate the problem of finding second-order stationary points (SOSP) in differentially private (DP) stochastic non-convex optimization. Existing methods suffer from two key limitations: (i) inaccurate convergence error rate due to…

机器学习 · 计算机科学 2026-01-21 Youming Tao , Zuyuan Zhang , Dongxiao Yu , Xiuzhen Cheng , Falko Dressler , Di Wang

In this paper, we study the problem of escaping from saddle points in smooth nonconvex optimization problems subject to a convex set $\mathcal{C}$. We propose a generic framework that yields convergence to a second-order stationary point of…

机器学习 · 计算机科学 2018-10-10 Aryan Mokhtari , Asuman Ozdaglar , Ali Jadbabaie

Optimizing non-convex functions is of primary importance in the vast majority of machine learning algorithms. Even though many gradient descent based algorithms have been studied, successive convex approximation based algorithms have been…

最优化与控制 · 数学 2019-03-06 Amrit Singh Bedi , Ketan Rajawat , Vaneet Aggarwal

Motivated by the super-diffusivity of self-repelling random walk, which has roots in statistical physics, this paper develops a new perturbation mechanism for optimization algorithms. In this mechanism, perturbations are adapted to the…

最优化与控制 · 数学 2022-03-29 Xin Guo , Jiequn Han , Mahan Tajrobehkar , Wenpin Tang

High-dimensional non-convex optimization problems in engineering design, control, and learning are often hindered by saddle points, flat plateaus, and strongly anisotropic curvature. This paper develops a unified, curvature-adaptive…

最优化与控制 · 数学 2025-09-04 Ronald Katende , Henry Kasumba

Smooth, non-convex optimization problems on Riemannian manifolds occur in machine learning as a result of orthonormality, rank or positivity constraints. First- and second-order necessary optimality conditions state that the Riemannian…

最优化与控制 · 数学 2019-10-24 Chris Criscitiello , Nicolas Boumal

Machine learning problems such as neural network training, tensor decomposition, and matrix factorization, require local minimization of a nonconvex function. This local minimization is challenged by the presence of saddle points, of which…

最优化与控制 · 数学 2018-07-23 Santiago Paternain , Aryan Mokhtari , Alejandro Ribeiro

Gradient descent is a popular algorithm in optimization, and its performance in convex settings is mostly well understood. In non-convex settings, it has been shown that gradient descent is able to escape saddle points asymptotically and…

机器学习 · 计算机科学 2022-08-17 Shiliang Zuo

Recent years have seen increased interest in performance guarantees of gradient descent algorithms for non-convex optimization. A number of works have uncovered that gradient noise plays a critical role in the ability of gradient descent…

最优化与控制 · 数学 2019-08-21 Stefan Vlaski , Ali H. Sayed

We analyze the variance of stochastic gradients along negative curvature directions in certain non-convex machine learning models and show that stochastic gradients exhibit a strong component along these directions. Furthermore, we show…

机器学习 · 计算机科学 2018-09-18 Hadi Daneshmand , Jonas Kohler , Aurelien Lucchi , Thomas Hofmann

We consider minimizing a nonconvex, smooth function $f$ on a Riemannian manifold $\mathcal{M}$. We show that a perturbed version of Riemannian gradient descent algorithm converges to a second-order stationary point (and hence is able to…

最优化与控制 · 数学 2019-06-19 Yue Sun , Nicolas Flammarion , Maryam Fazel

Gradient-related first-order methods have become the workhorse of large-scale numerical optimization problems. Many of these problems involve nonconvex objective functions with multiple saddle points, which necessitates an understanding of…

最优化与控制 · 数学 2022-03-10 Rishabh Dixit , Mert Gurbuzbalaban , Waheed U. Bajwa

Saddle points provide a hierarchical view of the energy landscape, revealing transition pathways and interconnected basins of attraction, and offering insight into the global structure, metastability, and possible collective mechanisms of…

数值分析 · 数学 2025-10-17 Baoming Shi , Lei Zhang , Qiang Du
‹ 上一页 1 2 3 10 下一页 ›