English
Related papers

Related papers: One-dimensional System Arising in Stochastic Gradi…

200 papers

We introduce an adaptive element-based domain decomposition (DD) method for solving saddle point problems defined as a block two by two matrix. The algorithm does not require any knowledge of the constrained space. We assume that all sub…

Distributed, Parallel, and Cluster Computing · Computer Science 2021-12-24 Frédéric Nataf , Pierre-Henri Tournier

We study the performance of stochastic first-order methods for finding saddle points of convex-concave functions. A notorious challenge faced by such methods is that the gradients can grow arbitrarily large during optimization, which may…

Machine Learning · Computer Science 2024-06-10 Gergely Neu , Nneka Okolo

We present a well-posedness result for strong solutions of one-dimensional stochastic differential equations (SDEs) of the form $$\mathrm{d} X= u(\omega,t,X)\, \mathrm{d} t + \frac12 \sigma(\omega,t,X)\sigma'(\omega,t,X)\,\mathrm{d} t +…

Probability · Mathematics 2022-10-18 Helge Holden , Kenneth H. Karlsen , Peter H. C. Pang

We study the stochastic optimization problem from a continuous-time perspective, with a focus on the Stochastic Gradient Descent with Momentum (SGDM) method. We show that the trajectory of SGDM, despite its \emph{stochastic} nature,…

Optimization and Control · Mathematics 2025-07-17 Yasong Feng , Yifan Jiang , Tianyu Wang , Zhiliang Ying

We derive stability criteria for saddle points of a class of nonsmooth optimization problems in Hilbert spaces arising in PDE-constrained optimization, using metric regularity of infinite-dimensional set-valued mappings. A main ingredient…

Optimization and Control · Mathematics 2017-02-13 Christian Clason , Tuomo Valkonen

We prove that various stochastic gradient descent methods, including the stochastic gradient descent (SGD), stochastic heavy-ball (SHB), and stochastic Nesterov's accelerated gradient (SNAG) methods, almost surely avoid any strict saddle…

Machine Learning · Computer Science 2023-02-16 Jun Liu , Ye Yuan

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…

Computational Physics · Physics 2025-01-17 Hendrik Schrautzer , Moritz Sallermann , Pavel F. Bessarab , Hannes Jónsson

We introduce and analyze Structured Stochastic Zeroth order Descent (S-SZD), a finite difference approach that approximates a stochastic gradient on a set of $l\leq d$ orthogonal directions, where $d$ is the dimension of the ambient space.…

Optimization and Control · Mathematics 2024-10-10 Marco Rando , Cesare Molinari , Silvia Villa , Lorenzo Rosasco

This paper analyzes the trajectories of stochastic gradient descent (SGD) to help understand the algorithm's convergence properties in non-convex problems. We first show that the sequence of iterates generated by SGD remains bounded and…

Optimization and Control · Mathematics 2020-06-22 Panayotis Mertikopoulos , Nadav Hallak , Ali Kavis , Volkan Cevher

We construct families of rational functions $f \colon \bP^1_k \to \bP^1_k$ of degree $d \geq 2$ over a perfect field $k$ whose associated fixed-point processes fail to be martingales. Conversely, for any normal variety $X \subset…

Number Theory · Mathematics 2026-04-09 Jianfei He , Zheng Zhu

Recent numerical developments in the study of glassy systems have shown that it is possible to give a purely geometric interpretation of the dynamic glass transition by considering the properties of unstable saddle points of the energy.…

Statistical Mechanics · Physics 2009-11-07 Andrea Cavagna , Irene Giardina , Giorgio Parisi

We present a unified framework based on primal-dual stochastic mirror descent for approximately solving infinite-horizon Markov decision processes (MDPs) given a generative model. When applied to an average-reward MDP with $A_{tot}$ total…

Machine Learning · Computer Science 2020-08-31 Yujia Jin , Aaron Sidford

We study the classical optimization problem $\min_{x \in \mathbb{R}^d} f(x)$ and analyze the gradient descent (GD) method in both nonconvex and convex settings. It is well-known that, under the $L$-smoothness assumption ($\|\nabla^2 f(x)\|…

Optimization and Control · Mathematics 2025-06-30 Alexander Tyurin

Consider $n$ agents connected over a network collaborating to minimize the average of their local cost functions combined with a common nonsmooth function. This paper introduces a unified algorithmic framework for solving such a problem…

Optimization and Control · Mathematics 2026-05-05 Kun Huang , Shi Pu , Angelia Nedić

In this paper, we investigate a stochastic approximation procedure $\left(X_n\right)_{n\ge 0}$ taking values in $R$. The process is adapted to a filtration $(F_n)_{n\ge 0}$ and satisfies the recursion…

Probability · Mathematics 2026-05-11 Jianan Shi , Qing Yin , Yu Miao

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…

Optimization and Control · Mathematics 2018-07-23 Santiago Paternain , Aryan Mokhtari , Alejandro Ribeiro

Gradient descent (GD) on logistic regression has many fascinating properties. When the dataset is linearly separable, it is known that the iterates converge in direction to the maximum-margin separator regardless of how large the step size…

Machine Learning · Computer Science 2025-07-16 Si Yi Meng , Baptiste Goujaud , Antonio Orvieto , Christopher De Sa

A central challenge to using first-order methods for optimizing nonconvex problems is the presence of saddle points. First-order methods often get stuck at saddle points, greatly deteriorating their performance. Typically, to escape from…

Machine Learning · Computer Science 2017-09-06 Sashank J Reddi , Manzil Zaheer , Suvrit Sra , Barnabas Poczos , Francis Bach , Ruslan Salakhutdinov , Alexander J Smola

Forward gradient descent (FGD) has been proposed as a biologically more plausible alternative of gradient descent as it can be computed without backward pass. Considering the linear model with $d$ parameters, previous work has found that…

Statistics Theory · Mathematics 2024-11-27 Niklas Dexheimer , Johannes Schmidt-Hieber

We derive a tight analysis of the trade-off function for Differentially Private Stochastic Gradient Descent (DP-SGD) with subsampling based on random shuffling within the $f$-DP framework. Our analysis covers the regime $\sigma \geq…

Machine Learning · Computer Science 2026-05-26 Marten van Dijk , Murat Bilgehan Ertan