4 papers
An Additively Preconditioned Trust Region Strategy for Machine Learning
Samuel Cruz Alegría, Bindi Çapriqi, Shega Likaj +2
Modern machine learning, especially the training of deep neural networks, depends on solving large-scale, highly nonconvex optimization problems, whose objective function exhibit a…
Data-Parallel Neural Network Training via Nonlinearly Preconditioned Trust-Region Method
Samuel A. Cruz Alegría, Ken Trotti, Alena Kopaničáková +1
Parallel training methods are increasingly relevant in machine learning (ML) due to the continuing growth in model and dataset sizes. We propose a variant of the Additively Precond…
Integrating Additive Multigrid with Multipreconditioned Conjugate Gradient Method
Hardik Kothari, Maria Giuseppina Chiara Nestola, Marco Favino +1
Due to its optimal complexity, the multigrid (MG) method is one of the most popular approaches for solving large-scale linear systems arising from the discretization of partial dif…
Parallel Trust-Region Approaches in Neural Network Training: Beyond Traditional Methods
Ken Trotti, Samuel A. Cruz Alegría, Alena Kopaničáková +1
We propose to train neural networks (NNs) using a novel variant of the ``Additively Preconditioned Trust-region Strategy'' (APTS). The proposed method is based on a parallelizable…