Saved in:
Bibliographic Details
Main Authors: Bhattacharjee, Abhinab, Popov, Andrey A., Sarshar, Arash, Sandu, Adrian
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2403.13704
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929499894972416
author Bhattacharjee, Abhinab
Popov, Andrey A.
Sarshar, Arash
Sandu, Adrian
author_facet Bhattacharjee, Abhinab
Popov, Andrey A.
Sarshar, Arash
Sandu, Adrian
contents The Adam optimizer, often used in Machine Learning for neural network training, corresponds to an underlying ordinary differential equation (ODE) in the limit of very small learning rates. This work shows that the classical Adam algorithm is a first-order implicit-explicit (IMEX) Euler discretization of the underlying ODE. Employing the time discretization point of view, we propose new extensions of the Adam scheme obtained by using higher-order IMEX methods to solve the ODE. Based on this approach, we derive a new optimization algorithm for neural network training that performs better than classical Adam on several regression and classification problems.
format Preprint
id arxiv_https___arxiv_org_abs_2403_13704
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Improving the Adaptive Moment Estimation (ADAM) stochastic optimizer through an Implicit-Explicit (IMEX) time-stepping approach
Bhattacharjee, Abhinab
Popov, Andrey A.
Sarshar, Arash
Sandu, Adrian
Computational Engineering, Finance, and Science
Machine Learning
Numerical Analysis
The Adam optimizer, often used in Machine Learning for neural network training, corresponds to an underlying ordinary differential equation (ODE) in the limit of very small learning rates. This work shows that the classical Adam algorithm is a first-order implicit-explicit (IMEX) Euler discretization of the underlying ODE. Employing the time discretization point of view, we propose new extensions of the Adam scheme obtained by using higher-order IMEX methods to solve the ODE. Based on this approach, we derive a new optimization algorithm for neural network training that performs better than classical Adam on several regression and classification problems.
title Improving the Adaptive Moment Estimation (ADAM) stochastic optimizer through an Implicit-Explicit (IMEX) time-stepping approach
topic Computational Engineering, Finance, and Science
Machine Learning
Numerical Analysis
url https://arxiv.org/abs/2403.13704