Year: 2025
Type: book-chapter
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 toward 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.
Source: De Gruyter eBooks
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W4409704506