English(EN) Posterior Frequencies and the Cost of Not Fitting: A Correction to a Memorization Lower Bound

新论文修正机器学习中的记忆下界

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-15 04:00

Zhenisbek Assylbekov 和 Lisa Feldman Barrett 在 arXiv 上发表的一篇新论文修正了先前确定的记忆下界。作者们为该界限的条件形式和平均形式提供了一个反例，证明了所提出的惩罚与实际超额风险之比可以呈指数级增长。他们提出使用全样本后验概率进行精确替换，该概率取决于重数和完整的频率分布，并描述了对无限制学习者有效的最大重数系数。 AI

影响改进了对机器学习模型中记忆的理论理解。

排序理由该集群包含一篇在 arXiv 上发表的研究论文，详细介绍了对机器学习中理论概念的修正。[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 →

本文如何被排名

Signal score: 14 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇在 arXiv 上发表的研究论文，详细介绍了对机器学习中理论概念的修正。[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]

arXiv cs.LG TIER_1 English(EN) · Zhenisbek Assylbekov, Rustem Takhanov · 2026-10-15 04:00

后验频率与不拟合的代价：对记忆下界的修正

arXiv:2610.20402v1 Announce Type: cross Abstract: Feldman's memorization lower bound assigns a frequency coefficient based on how often a point appears in the training sample. We give an exact three-point counterexample to its conditional and averaged forms, using independent fai…

本文如何被排名

报道来源 [1]

后验频率与不拟合的代价：对记忆下界的修正

相关实体

相关话题