English
Related papers

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

200 papers

We provide larger step-size restrictions for which gradient descent based algorithms (almost surely) avoid strict saddle points. In particular, consider a twice differentiable (non-convex) objective function whose gradient has Lipschitz…

Machine Learning · Statistics 2019-08-06 Hayden Schaeffer , Scott G. McCalla

We study the weak limits of solutions to SDEs \[dX_n(t)=a_n\bigl(X_n(t)\bigr)\,dt+dW(t),\] where the sequence $\{a_n\}$ converges in some sense to $(c_- 1\mkern-4.5mu\mathrm{l}_{x<0}+c_+ 1\mkern-4.5mu\mathrm{l}_{x>0})/x+\gamma\delta_0$.…

Probability · Mathematics 2016-11-23 Andrey Pilipenko , Yuriy Prykhodko

We study the saddlepoint approximation (SPA) for sums of $n$ i.i.d. random vectors $X_i\in\mathbb R^d$ in growing dimensions. SPA provides highly accurate approximations to probability densities and distribution functions via the moment…

Probability · Mathematics 2025-10-27 Alexander Katsevich

In this paper we investigate the convergence of a recently popular class of first-order primal-dual algorithms for saddle point problems under the presence of errors occurring in the proximal maps and gradients. We study several types of…

Optimization and Control · Mathematics 2020-02-26 Julian Rasch , Antonin Chambolle

This paper considers continuously differentiable functions of two vector variables that have (possibly a continuum of) min-max saddle points. We study the asymptotic convergence properties of the associated saddle-point dynamics…

Optimization and Control · Mathematics 2016-11-03 Ashish Cherukuri , Bahman Gharesifard , Jorge Cortes

We study the stochastic differential equation $dX_t = A(X_{t-}) \, dZ_t$, $ X_0 = x$, where $Z_t = (Z_t^{(1)},\ldots,Z_t^{(d)})^T$ and $Z_t^{(1)}, \ldots, Z_t^{(d)}$ are independent one-dimensional L{\'e}vy processes with characteristic…

Probability · Mathematics 2019-10-08 Tadeusz Kulczycki , Michal Ryznar

In this paper we propose a primal-dual proximal extragradient algorithm to solve the generalized Dantzig selector (GDS) estimation problem, based on a new convex-concave saddle-point (SP) reformulation. Our new formulation makes it possible…

Machine Learning · Statistics 2016-06-03 Sangkyun Lee , Damian Brzyski , Malgorzata Bogdan

Nesterov's accelerated gradient descent (AGD), an instance of the general family of "momentum methods", provably achieves faster convergence rate than gradient descent (GD) in the convex setting. However, whether these methods are superior…

Machine Learning · Computer Science 2017-11-29 Chi Jin , Praneeth Netrapalli , Michael I. Jordan

Let $d \ge 2$. In this paper, we study weak solutions for the following type of stochastic differential equation \[ dX_{t}=dS_{t}+b(s+t, X_{t})dt, \quad X_{0}=x, \] where $(s,x)\in \mathbb{R}_+ \times \mathbb{R}^{d}$ is the initial starting…

Probability · Mathematics 2015-12-10 Peng Jin

We analyze the stochastic proximal subgradient descent in the case where the objective functions are path differentiable and verify a Sard-type condition. While the accumulation set may not be reduced to unique point, we show that the time…

Optimization and Control · Mathematics 2022-05-25 Sholom Schechtman

Inverse problems in scientific computing often require optimization over infinite-dimensional Hilbert spaces. A commonly used solver in such settings is stochastic gradient descent (SGD), where gradients are approximated using randomly…

Optimization and Control · Mathematics 2026-04-14 Sandra Cerrai , Qin Li , Anjali Nair , Jaeyoung Yoon

We consider a dynamical system undergoing a saddle-node bifurcation with an explicitly time dependent parameter~$p(t)$. The combined dynamics can be considered as a dynamical systems where $p$ is a slowly evolving parameter. Here, we…

Chaotic Dynamics · Physics 2024-01-19 Elias Enache , Oleksandr Kozak , Nico Wunderling , Jürgen Vollmer

We study several one dimensional step flow models. Numerical simulations show that the slope of the profile exhibits scaling in all cases. We apply a scaling ansatz to the various step flow models and investigate their long time evolution.…

Materials Science · Physics 2009-10-31 Navot Israeli , Hyeong-Chai Jeong , Daniel Kandel , John D. Weeks

This paper addresses a continuous-time risk-minimizing two-player zero-sum stochastic differential game (SDG), in which each player aims to minimize its probability of failure. Failure occurs in the event when the state of the game enters…

Optimization and Control · Mathematics 2023-08-23 Apurva Patil , Yujing Zhou , David Fridovich-Keil , Takashi Tanaka

Stochastic dynamical systems allow modelling of transitions induced by disturbances, in particular from an attracting equilibrium and crossing the stable manifold of a saddle. In the small-noise limit, the probability of such transitions is…

Statistical Mechanics · Physics 2025-09-05 Jiayao Shao , Tobias Grafke , Robert S. MacKay

This paper discusses the first exit and Dirichlet problems of the nonisotropic tempered $\alpha$-stable process $X_t$. The upper bounds of all moments of the first exit position $\left|X_{\tau_D}\right|$ and the first exit time $\tau_D$ are…

Probability · Mathematics 2019-01-11 Xing Liu , Weihua Deng

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…

Optimization and Control · Mathematics 2019-03-06 Amrit Singh Bedi , Ketan Rajawat , Vaneet Aggarwal

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…

Optimization and Control · Mathematics 2023-07-17 Yassine Laguel , Necdet Serhat Aybat , Mert Gürbüzbalaban

Given a stochastic dynamical system modelled via stochastic differential equations (SDEs), we evaluate the safety of the system through characterizations of its exit time moments. We lift the (possibly nonlinear) dynamics into the space of…

Systems and Control · Electrical Eng. & Systems 2022-09-19 Peter Du , Katherine Driggs-Campbell , Roy Dong

We show that convex-concave Lipschitz stochastic saddle point problems (also known as stochastic minimax optimization) can be solved under the constraint of $(\epsilon,\delta)$-differential privacy with \emph{strong (primal-dual) gap} rate…

Machine Learning · Computer Science 2023-06-30 Raef Bassily , Cristóbal Guzmán , Michael Menart