paper-with-me

Papers

Stochastic Modified Equations and Dynamics of Stochastic Gradient Algorithms I: Mathematical Foundations

2018-11-05 · Qianxiao Li, Cheng Tai, Weinan E

We develop the mathematical foundations of the stochastic modified equations (SME) framework for analyzing the dynamics of stochastic gradient algorithms, where the latter is approximated by a class of stochastic differential equations with small noise parameters. We prove that this approximation can be understood mathematically as an weak approximation, which leads to a number of precise and useful results on the approximations of stochastic gradient descent (SGD), momentum SGD and stochastic Nesterov's accelerated gradient method in the general setting of stochastic objectives. We also demonstrate through explicit calculations that this continuous-time approach can uncover important analytical insights into the stochastic gradient algorithms under consideration that may not be easy to obtain in a purely discrete-time setting.

📄 PDF Abstract BibTeX arXiv:1811.01558

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 Modified Flows, Mean-Field Limits and Dynamics of Stochastic Gradient Descent

2023-02-14 · Benjamin Gess, Sebastian Kassing, Vitalii Konarovskyi

We propose new limiting dynamics for stochastic gradient descent in the small learning rate regime called stochastic modified flows. These SDEs are driven by a cylindrical Brownian motion and improve the so-called stocha…

Backward error analysis and the qualitative behaviour of stochastic optimization algorithms: Application to stochastic coordinate descent

2023-09-05 · Stefano Di Giovacchino, Desmond J. Higham, Konstantinos Zygalakis

Stochastic optimization methods have been hugely successful in making large-scale optimization problems feasible when computing the full gradient is computationally prohibitive. Using the theory of modified equations for…

Stochastic Optimization

Stochastic modified equations for the asynchronous stochastic gradient descent

2018-05-21 · Jing An, Jianfeng Lu, Lexing Ying

We propose a stochastic modified equations (SME) for modeling the asynchronous stochastic gradient descent (ASGD) algorithms. The resulting SME of Langevin type extracts more information about the ASGD dynamics and eluci…

Stochastic Modified Equations for Continuous Limit of Stochastic ADMM

2020-03-07 · Xiang Zhou, Huizhuo Yuan, Chris Junchi Li, Qingyun Sun

Stochastic version of alternating direction method of multiplier (ADMM) and its variants (linearized ADMM, gradient-based ADMM) plays a key role for modern large scale machine learning problems. One example is the regula…

Effective continuous equations for adaptive SGD: a stochastic analysis view

2025-09-25 · Luca Callisti, Marco Romito, Francesco Triggiano arxiv

We present a theoretical analysis of some popular adaptive Stochastic Gradient Descent (SGD) methods in the small learning rate regime. Using the stochastic modified equations framework introduced by Li et al., we derive…