PulseAugur
实时 10:11:58
English(EN) AdaMeZO: Adam-style Zeroth-Order Optimizer for LLM Fine-tuning Without Maintaining the Moments

AdaMeZO优化器通过Adam风格估计减少LLM微调的内存需求

研究人员推出AdaMeZO,这是一种新颖的优化器,旨在提高大型语言模型微调的内存效率。与需要大量GPU内存进行反向传播的传统方法不同,AdaMeZO采用零阶方法。它模仿Adam的动量估计,但没有内存开销,旨在提高现有节省内存的技术(如MeZO)的收敛速度。实验表明,AdaMeZO可以用显著更少的正向传播次数实现更好的性能。 AI

影响 为LLM提供了一种更节省内存的微调方法,有可能降低研究人员和开发者的硬件要求。

排序理由 该集群包含一篇arXiv预印本,详细介绍了一种用于LLM微调的新优化方法。

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →

AdaMeZO优化器通过Adam风格估计减少LLM微调的内存需求

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
Research
该集群包含一篇arXiv预印本,详细介绍了一种用于LLM微调的新优化方法。
Source corroboration
2 independent sources
Multiple independent publishers reporting the same story raises confidence that it's real and newsworthy.
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
122 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 [2]

  1. arXiv cs.LG TIER_1 English(EN) · Zhijie Cai, Haolong Chen, Guangxu Zhu ·

    AdaMeZO:一种无需维护动量的 Adam 式零阶优化器用于 LLM 微调

    arXiv:2605.00650v1 Announce Type: new Abstract: Fine-tuning LLMs is necessary for various dedicated downstream tasks, but classic backpropagation-based fine-tuning methods require substantial GPU memory. To this end, a recent work, MeZO, which relies solely on forward passes to f…

  2. arXiv cs.AI TIER_1 English(EN) · Guangxu Zhu ·

    AdaMeZO:一种无需维护矩的Adam风格零阶优化器用于LLM微调

    Fine-tuning LLMs is necessary for various dedicated downstream tasks, but classic backpropagation-based fine-tuning methods require substantial GPU memory. To this end, a recent work, MeZO, which relies solely on forward passes to fine-tune LLMs, significantly reduces GPU require…