PulseAugur
中
实时 23:42:20
English(EN) Anytime Pretraining: Horizon-Free Learning-Rate Schedules with Weight Averaging

Anytime Pretraining 采用无视界 LLM 训练和权重平均

作者 PulseAugur 编辑部 · [1 个来源] ·

研究人员推出了一种新颖的大型语言模型训练方法“Anytime Pretraining”，该方法无需预定义训练视界。该方法结合了无视界学习率调度和权重平均，在最终损失方面与传统的余弦衰减调度相当。研究结果表明，这种随时可用的策略为大型语言模型预训练提供了一种实用且有效的方法，尤其是在开放式训练场景中。 AI

影响 这项研究通过消除对复杂、依赖视界的学习率调度的需求，有望简化 LLM 训练。

排序理由 该集群包含一篇详细介绍大型语言模型新训练方法的论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv stat.ML 阅读 →

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

Anytime Pretraining 采用无视界 LLM 训练和权重平均

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
该集群包含一篇详细介绍大型语言模型新训练方法的论文。[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, infra
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
64 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 stat.ML TIER_1 English(EN) · Alexandru Meterez, Pranav Ajit Nair, Depen Morwani, Cengiz Pehlevan, Sham Kakade ·

    随时预训练：无视界学习率调度与权重平均

    arXiv:2602.03702v2 Announce Type: replace-cross Abstract: Large language models are increasingly trained in continual or open-ended settings, where the total training horizon is not known in advance. Despite this, most existing pretraining recipes are not anytime: they rely on ho…

相关实体

相关话题