DOE OSTI · 3028308
Improving ADAM through an implicit-explicit (IMEX) time-stepping approach
Abstract
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. Here, 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.
Explore related subjects
Keep this discovery
Explore connections, maps & timelines
Bhattacharjee, Abhinab, Popov, Andrey A., Sarshar, Arash, Sandu, Adrian. 2024-08-23. Improving ADAM through an implicit-explicit (IMEX) time-stepping approach. https://doi.org/10.1615/jmachlearnmodelcomput.2024053508. https://searchnasa.com/record/osti%3A3028308/improving-adam-through-an-implicit-explicit-imex-time-stepping-approach
Citations retain the original authors and DOI and include this site’s record URL. If this discovery service contributed to your research, you can also cite Search NASA by Indiciae: BibTeX · RIS.