PulseAugur
中
实时 03:24:21
English(EN) An Elementary Proof of the Near Optimality of LogSumExp Smoothing

LogSumExp平滑在最大函数逼近中近乎最优

一篇新发表在arXiv上的论文提供了一个初等证明,证明了LogSumExp平滑在$\\mathbb{R}^d$中逼近最大函数时近乎最优。该研究为高估平滑度设定了一个下界,表明它们必须至少相差d的自然对数的约0.8145倍。虽然LogSumExp接近这个界限,但该论文也引入了严格更强的平滑方法,并针对低维度提出了完全最优的平滑方法,这些方法达到了已设定的下界。 AI

影响 为机器学习模型中使用的优化技术的理论基础提供了支持。

排序理由 发表在arXiv上的学术论文,详细介绍了数学证明和新构造。[lever_c_demoted from research: ic=1 ai=0.7]

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 →

LogSumExp平滑在最大函数逼近中近乎最优

本文如何被排名

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
发表在arXiv上的学术论文,详细介绍了数学证明和新构造。[lever_c_demoted from research: ic=1 ai=0.7]
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
88 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

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) · Thabo Samakhoana, Benjamin Grimmer ·

    LogSumExp平滑的近乎最优性的初等证明

    arXiv:2512.10825v3 Announce Type: replace-cross Abstract: We consider the design of smoothings of the (coordinate-wise) max function in $\mathbb{R}^d$ in the infinity norm. The LogSumExp function $f(x)=\ln(\sum^d_i\exp(x_i))$ provides a classical smoothing, differing from the max…