The article discusses the use of second-order solvers in scientific machine learning (SciML) for regression tasks. It introduces a software framework based on PETSc to bridge deep-learning software with conventional solvers. Empirical evidence shows the efficacy of trust region methods based on Gauss-Newton approximation in improving generalization errors. The content is structured into sections discussing the introduction, background, related work, contributions, and numerical results of various test cases.
To Another Language
from source content
arxiv.org
Thông tin chi tiết chính được chắt lọc từ
by Stefano Zamp... lúc arxiv.org 03-20-2024
https://arxiv.org/pdf/2403.12188.pdfYêu cầu sâu hơn