paper-with-me

홈 › Papers

Almost Sure Saddle Avoidance of Stochastic Gradient Methods without the Bounded Gradient Assumption

2023-02-15 · Jun Liu, Ye Yuan

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 manifold. To the best of our knowledge, this is the first time such results are obtained for SHB and SNAG methods. Moreover, our analysis expands upon previous studies on SGD by removing the need for bounded gradients of the objective function and uniformly bounded noise. Instead, we introduce a more practical local boundedness assumption for the noisy gradient, which is naturally satisfied in empirical risk minimization problems typically seen in training of neural networks.

📄 PDF Abstract BibTeX arXiv:2302.07862

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

SGD Stochastic Gradient Descent is an iterative optimization technique that uses minibatches of data to form an expectation of the gradient, rather than the full gradient using…

Similar Papers 제목 키워드 기반

Stochastic Saddle Avoidance Beyond Unit Excitation and Smoothness: A Pathwise Lyapunov-Perron Framework

2026-08-04 · Junwen Qiu, Bohao Ma, Andre Milzarek, Junyu Zhang arxiv

Unit excitation (UE) is a common assumption in stochastic saddle avoidance: the stochastic error must have a uniformly positive component along every direction, in expectation. This condition gives a direct way to rule o…

Stochastic Optimization

Stochastic optimization with momentum: convergence, fluctuations, and traps avoidance

2020-12-07 · A. Barakat, P. Bianchi, W. Hachem, Sh. Schechtman

In this paper, a general stochastic optimization procedure is studied, unifying several variants of the stochastic gradient descent such as, among others, the stochastic heavy ball method, the Stochastic Nesterov Acceler…

Stochastic Optimization

A Stochastic Bregman Primal-Dual Splitting Algorithm for Composite Optimization

2021-12-22 · Antonio Silveti-Falls, Cesare Molinari, Jalal Fadili

We study a stochastic first order primal-dual method for solving convex-concave saddle point problems over real reflexive Banach spaces using Bregman divergences and relative smoothness assumptions, in which we allow for…

On the modes of convergence of Stochastic Optimistic Mirror Descent (OMD) for saddle point problems

2019-08-02 · Yanting Ma, Shuchin Aeron, Hassan Mansour

In this article, we study the convergence of Mirror Descent (MD) and Optimistic Mirror Descent (OMD) for saddle point problems satisfying the notion of coherence as proposed in Mertikopoulos et al. We prove convergence o…

Constrained Reinforcement Learning via Dissipative Saddle Flow Dynamics

2022-12-03 · Tianqi Zheng, Pengcheng You, Enrique Mallada

In constrained reinforcement learning (C-RL), an agent seeks to learn from the environment a policy that maximizes the expected cumulative reward while satisfying minimum requirements in secondary cumulative reward const…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)