Search Results for author: Mohammad Deghat

Found 1 papers, 0 papers with code

AA-DLADMM: An Accelerated ADMM-based Framework for Training Deep Neural Networks

no code implementations8 Jan 2024 Zeinab Ebrahimi, Gustavo Batista, Mohammad Deghat

The main intention of the AA-DLADMM algorithm is to employ Anderson acceleration to ADMM by considering it as a fixed-point iteration and attaining a nearly quadratic convergence rate.

Cannot find the paper you are looking for? You can Submit a new open access paper.