中文
相关论文

相关论文: Multiscale Gentlest Ascent Dynamics for Saddle Poi…

200 篇论文

Loss functions with a large number of saddle points are one of the major obstacles for training modern machine learning models efficiently. First-order methods such as gradient descent are usually the methods of choice for training machine…

机器学习 · 计算机科学 2020-09-29 Lisa Maria Kreusser , Stanley J. Osher , Bao Wang

To obtain explicit understanding of the behavior of dynamical systems, geometrical methods and slow-fast analysis have proved to be highly useful. Such methods are standard for smooth dynamical systems, and increasingly used for continuous,…

定量方法 · 定量生物学 2023-10-19 Francesco Montefusco , Morten Gram Pedersen

We use martingale and stochastic analysis techniques to study a continuous-time optimal stopping problem, in which the decision maker uses a dynamic convex risk measure to evaluate future rewards. We also find a saddle point for an…

概率论 · 数学 2009-11-23 Erhan Bayraktar , Ioannis Karatzas , Song Yao

Stochastic gradient descent with momentum (SGDM) methods have become fundamental optimization tools in machine learning, combining the computational efficiency of stochastic gradients with the acceleration benefits of momentum. Despite…

最优化与控制 · 数学 2026-03-02 Zimeng Wang , Alp Yurtsever

We analyze the behavior of randomized coordinate gradient descent for nonconvex optimization, proving that under standard assumptions, the iterates almost surely escape strict saddle points. By formulating the method as a nonlinear random…

最优化与控制 · 数学 2025-08-12 Ziang Chen , Yingzhou Li , Zihao Li

The properties of higher-index saddle points have been invoked in recent theories of the dynamics of supercooled liquids. Here we examine in detail a mapping of configurations to saddle points using minimization of $|\nabla E|^2$, which has…

无序系统与神经网络 · 物理学 2007-05-23 Jonathan P. K. Doye , David J. Wales

A game theory inspired methodology is proposed for finding a function's saddle points. While explicit descent methods are known to have severe convergence issues, implicit methods are natural in an adversarial setting, as they take the…

最优化与控制 · 数学 2019-06-04 Montacer Essid , Esteban Tabak , Giulio Trigila

We present an improved high-index saddle dynamics (iHiSD) for finding saddle points and constructing solution landscapes, which is a crossover dynamics from gradient flow to traditional HiSD such that the Morse theory for gradient flow…

数值分析 · 数学 2025-10-22 Hua Su , Haoran Wang , Lei Zhang , Jin Zhao , Xiangcheng Zheng

We consider stochastic strongly-convex-strongly-concave (SCSC) saddle point (SP) problems which frequently arise in applications ranging from distributionally robust learning to game theory and fairness in machine learning. We focus on the…

最优化与控制 · 数学 2023-07-17 Yassine Laguel , Necdet Serhat Aybat , Mert Gürbüzbalaban

Efficient skill acquisition, representation, and on-line adaptation to different scenarios has become of fundamental importance for assistive robotic applications. In the past decade, dynamical systems (DS) have arisen as a flexible and…

机器人学 · 计算机科学 2020-03-27 Matteo Saveriano , Dongheui Lee

SGD with momentum (SGDM) has been widely applied in many machine learning tasks, and it is often applied with dynamic stepsizes and momentum weights tuned in a stagewise manner. Despite of its empirical advantage over SGD, the role of…

最优化与控制 · 数学 2020-08-19 Yanli Liu , Yuan Gao , Wotao Yin

Under appropriate cooperation protocols and parameter choices, fully decentralized solutions for stochastic optimization have been shown to match the performance of centralized solutions and result in linear speedup (in the number of…

多智能体系统 · 计算机科学 2019-10-31 Stefan Vlaski , Ali H. Sayed

The framework of transition state theory (TST) provides a powerful way for analyzing the dynamics of physical and chemical reactions. While TST has already been successfully used to obtain reaction rates for systems with a single…

化学物理 · 物理学 2021-02-26 Johannes Reiff , Matthias Feldmaier , Jörg Main , Rigoberto Hernandez

This paper is a survey of methods for solving smooth (strongly) monotone stochastic variational inequalities. To begin with, we give the deterministic foundation from which the stochastic methods eventually evolved. Then we review methods…

最优化与控制 · 数学 2023-04-04 Aleksandr Beznosikov , Boris Polyak , Eduard Gorbunov , Dmitry Kovalev , Alexander Gasnikov

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

A method for locating first order saddle points on the energy surface of a magnetic system is described and several applications presented where the mechanism of various magnetic transitions is identified. The starting point for the…

计算物理 · 物理学 2025-01-17 Hendrik Schrautzer , Moritz Sallermann , Pavel F. Bessarab , Hannes Jónsson

We propose stochastic variance reduced algorithms for solving convex-concave saddle point problems, monotone variational inequalities, and monotone inclusions. Our framework applies to extragradient, forward-backward-forward, and…

最优化与控制 · 数学 2022-06-14 Ahmet Alacaoglu , Yura Malitsky

Modern optimal control theory involves adjoining the already known equations of motion of a dynamic system to the objective function using dynamic costates; this is done in order to constrain the optimal control solutions to satisfy the…

最优化与控制 · 数学 2026-05-25 Ossama Abdelkhalik , Aimar Negrete

Stochastic gradient methods are scalable for solving large-scale optimization problems that involve empirical expectations of loss functions. Existing results mainly apply to optimization problems where the objectives are one- or two-level…

最优化与控制 · 数学 2018-01-15 Shuoguang Yang , Mengdi Wang , Ethan X. Fang

Many enhanced sampling techniques rely on the identification of a number of collective variables that describe all the slow modes of the system. By constructing a bias potential in this reduced space one is then able to sample efficiently…

计算物理 · 物理学 2019-03-05 Michele Invernizzi , Michele Parrinello