paper-with-me

홈 › Papers

A Non-Monotone Preconditioned Trust-Region Method for Neural Network Training

2026-05-14 · Andrea Angino, Bindi Çapriqi, Shega Likaj, Ken Trotti, Rolf Krause arxiv

Training deep neural networks at scale can benefit from domain decomposition, where the network is split into subdomains trained in parallel and coupled by a global trust-region mechanism. Building on the Additively Preconditioned Trust-Region Strategy (APTS), we propose a non-monotone variant with a nonlinear additive Schwarz preconditioner that combines parallel subdomain corrections with global coarse-space directions. A windowed acceptance criterion allows controlled objective increases, avoiding needless rejection of effective coarse steps. The resulting non-monotone APTS (NAPTS) preserves accuracy while reducing CPU time by 30\% and cutting rejected steps to one third of those in APTS.

📄 PDF Abstract BibTeX arXiv:2605.14860

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Data-Parallel Neural Network Training via Nonlinearly Preconditioned Trust-Region Method

2025-02-07 · Samuel A. Cruz Alegría, Ken Trotti, Alena Kopaničáková, Rolf Krause

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 Preconditioned Trust-Region Strategy (APTS) for…

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

2023-12-21 · Ken Trotti, Samuel A. Cruz Alegría, Alena Kopaničáková, Rolf Krause

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 a…

A Neural-Operator Preconditioned Newton Method for Accelerated Nonlinear Solvers

2025-11-11 · Youngkyu Lee, Shanqing Liu, Jerome Darbon, George Em Karniadakis arxiv

We propose a novel neural preconditioned Newton (NP-Newton) method for solving parametric nonlinear systems of equations. To overcome the stagnation or instability of Newton iterations caused by unbalanced nonlinearities…

Computational Efficiency

Stochastic Trust Region Inexact Newton Method for Large-scale Machine Learning

2018-12-26 · Vinod Kumar Chauhan, Anuj Sharma, Kalpana Dahiya

Nowadays stochastic approximation methods are one of the major research direction to deal with the large-scale machine learning problems. From stochastic first order methods, now the focus is shifting to stochastic secon…

BIG-bench Machine LearningSecond-order methods

Spingarn's Method and Progressive Decoupling Beyond Elicitable Monotonicity

2025-04-01 · Brecht Evens, Puya Latafat, Panagiotis Patrinos

Spingarn's method of partial inverses and the progressive decoupling algorithm address inclusion problems involving the sum of an operator and the normal cone of a linear subspace, known as linkage problems. Despite thei…