English(EN) Landau theory of quenched criticality in linear in-context learning

朗道理论解释线性上下文学习中的临界性

作者 PulseAugur 编辑部 · [1 个来源] · 2026-08-31 04:00

研究人员开发了一种朗道理论来解释在线性上下文学习（ICL）中观察到的临界现象。该理论将预训练样本数量接近可学习参数数量时出现的双下降奇点视为淬灭无序系统中的临界现象。该研究将学习参数的样本到样本的波动确定为该奇点的根本原因，并建立了序参量与经验弛豫矩阵特征值之间的关系。 AI

影响为理解线性上下文学习中的插值临界性提供了统计物理学框架。

排序理由该集群包含一篇研究论文，详细介绍了理解机器学习中一种现象的新理论框架。[lever_c_demoted from research: ic=1 ai=1.0]

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: 13 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇研究论文，详细介绍了理解机器学习中一种现象的新理论框架。[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。

arXiv cs.LG TIER_1 English(EN) · Daesik Kim, Sumin Choi, Hyojae Jeon, Jung Hoon Han · 2026-08-31 04:00

Landau theory of quenched criticality in linear in-context learning

arXiv:2608.28059v1 Announce Type: cross Abstract: In-context learning (ICL) allows a pretrained model to infer a new task from examples supplied in its prompt without updating its parameters. In linear models of ICL, the prediction error develops a double-descent singularity when…