PulseAugur
实时 06:54:01
English(EN) Inference for Newton Methods with Accelerated Sketch-and-Project via Random Scaling

新的牛顿法推理方法加速收敛

研究人员开发了一种新颖的在线草图牛顿法,它使用广义加速草图与投影求解器(GAS)来近似牛顿方向,解决了传统二阶方法的计算瓶颈。该GAS求解器结合了Nesterov动量以加速收敛,并允许灵活的投影度量以降低计算成本。研究建立了平均草图牛顿迭代的渐近正态性,并表征了它们的极限协方差矩阵,表明其比加速方法产生的最后一次迭代收敛得更快且更小。此外,证明了一个泛函中心极限定理,它能够基于随机缩放进行在线推理,从而绕过显式协方差估计并获得渐近有效的结果,这已通过数值实验得到证明。 AI

影响 引入了一种更有效的优化方法推理程序,可能影响AI模型训练。

排序理由 该集群包含一篇关于牛顿法新推理方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.LG 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →

新的牛顿法推理方法加速收敛

本文如何被排名

Signal score
26 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
该集群包含一篇关于牛顿法新推理方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
paper, other
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Breaking (< 6h)
Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准

报道来源 [1]

  1. arXiv cs.LG TIER_1 English(EN) · Xinchen Du, Elizaveta Rebrova, Micha{\l} Derezi\'{n}ski, Sen Na ·

    具有随机缩放加速草图与投影的牛顿法推理

    arXiv:2609.12421v1 Announce Type: cross Abstract: We study an online sketched Newton method that approximates the Newton direction at each step via a state-of-the-art sketching solver, called the generalized accelerated sketch-and-project solver (GAS), thereby mitigating the comp…