NAPTS extends APTS with non-monotone acceptance and nonlinear Schwarz preconditioning to reduce CPU time by 30% and rejected steps by two-thirds while preserving accuracy in neural network training.
arXiv preprint arXiv:2512.14286 (2025) 6
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.OC 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
A Non-Monotone Preconditioned Trust-Region Method for Neural Network Training
NAPTS extends APTS with non-monotone acceptance and nonlinear Schwarz preconditioning to reduce CPU time by 30% and rejected steps by two-thirds while preserving accuracy in neural network training.