跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2611.24113 · v1

AG-BFGS: Foundations for Accelerated Geometry Learning

首次提交 2026-11-18 17:29
版本更新 2026-11-18 17:29
雷达观测 2026-11-19 15:04
arXiv ↗PDF ↗

摘要

We introduce an accelerated geometry-learning framework for BFGS that incorporates momentum into the learning of Hessian inverse approximations. We prove that the resulting accelerated updates satisfy explicit stability conditions and preserve positive definiteness within admissible parameter regions. Numerical experiments demonstrate consistent improvements over the corresponding non-accelerated schemes while maintaining numerical stability. These results provide the first rigorous theoretical foundation for accelerated quasi-Newton learning and bridge the gap between empirical observations and mathematical guarantees for accelerated second-order methods.

作者备注:19 pages, 7 figures

AI 论文解读

基于摘要 · 非全文审阅

此版本尚未生成 AI 解读。解读由后台任务生成并按论文版本保存,登录后共享已有结果。

版本差异

目前只收录了一个版本。收录下一版后,可以对照标题、作者、分类和摘要。

观测到的版本

相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。

v1 · 2026-11-18 17:29 · 最新观测版本

AG-BFGS: Foundations for Accelerated Geometry Learning

We introduce an accelerated geometry-learning framework for BFGS that incorporates momentum into the learning of Hessian inverse approximations. We prove that the resulting accelerated updates satisfy explicit stability conditions and preserve positive definiteness within admissible parameter regions. Numerical experiments demonstrate consistent improvements over the corresponding non-accelerated schemes while maintaining numerical stability. These results provide the first rigorous theoretical foundation for accelerated quasi-Newton learning and bridge the gap between empirical observations and mathematical guarantees for accelerated second-order methods.

查看此版本解读 →查看此版本原文 ↗