English

Parallel Trust-Region Approaches in Neural Network Training: Beyond Traditional Methods

Numerical Analysis 2023-12-22 v1 Machine Learning Numerical Analysis

Abstract

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 additive domain decomposition approach applied to the neural network's parameters. Built upon the TR framework, the APTS method ensures global convergence towards a minimizer. Moreover, it eliminates the need for computationally expensive hyper-parameter tuning, as the TR algorithm automatically determines the step size in each iteration. We demonstrate the capabilities, strengths, and limitations of the proposed APTS training method by performing a series of numerical experiments. The presented numerical study includes a comparison with widely used training methods such as SGD, Adam, LBFGS, and the standard TR method.

Keywords

Cite

@article{arxiv.2312.13677,
  title  = {Parallel Trust-Region Approaches in Neural Network Training: Beyond Traditional Methods},
  author = {Ken Trotti and Samuel A. Cruz Alegría and Alena Kopaničáková and Rolf Krause},
  journal= {arXiv preprint arXiv:2312.13677},
  year   = {2023}
}
R2 v1 2026-06-28T13:58:28.115Z