PulseAugur
中
实时 14:54:07

新方法以更低的计算成本加速神经架构搜索 · 跟踪3个来源

作者 PulseAugur 编辑部 · [4 个来源] ·

研究人员开发了改进神经架构搜索（NAS）的新方法，该过程可能计算成本高昂。一种名为RiPPLE的方法使用来自一小组锚定架构的局部训练数据来预测许多其他架构的性能，从而减少了完全训练的需要。另一种方法CoRA-NAS结合了架构的粗略排序和一个细化阶段，该阶段通过外推早期训练曲线来估计性能，成本大大降低。第三种技术通过提出一种无泄漏的、基于块的方法来解决NAS中Leave-One-Subject-Out（LOSO）评估的成本问题，该方法在不同受试者之间共享计算，从而在保持准确性的同时大大降低了资源需求。 AI

影响 这些方法旨在显著降低寻找最优神经网络架构的计算成本，从而可能加速AI的开发和部署。

排序理由 该集群包含多篇介绍神经架构搜索新方法的学术论文。

在 Hugging Face Daily Papers 阅读 →

AI 生成摘要 · Google Gemini · 来自 4 个来源。 我们如何撰写摘要 →

新方法以更低的计算成本加速神经架构搜索 · 跟踪3个来源

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
该集群包含多篇介绍神经架构搜索新方法的学术论文。
Source corroboration
4 independent sources
Strong cross-source corroboration — multiple independent publishers covered this within the clustering window.
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
46 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 [4]

  1. arXiv cs.LG TIER_1 English(EN) · Yifan Yang, Zhaoyan Wang, Zheng Gao, Xiaoyu Li, Jiaojiao Jiang ·

    RiPPLE：从早期训练中进行跨空间性能预测以实现神经架构搜索

    arXiv:2609.12418v1 Announce Type: new Abstract: Neural architecture search (NAS) evaluates candidate networks, but fully training enough architectures to rank an entire space is expensive. Zero-cost proxies score architectures at initialization, yet their ranking quality varies a…

  2. arXiv cs.AI TIER_1 English(EN) · Heinke Hihn ·

    Leave-One-Subject-Out 评估下的高效无泄漏神经架构搜索

    arXiv:2609.09433v1 Announce Type: cross Abstract: Leave-One-Subject-Out (LOSO) evaluation estimates generalisation performance for subject-based classification but makes Neural Architecture Search (NAS) computationally expensive because a fully nested implementation requires N in…

  3. arXiv cs.LG TIER_1 English(EN) · Yifan Yang, Zhaoyan Wang, Zheng Gao, Xiaoyu Li, Jiaojiao Jiang ·

    CoRA-NAS：神经架构搜索的粗粒度排序和锚点残差细化

    arXiv:2609.11884v1 Announce Type: new Abstract: Zero-cost proxies rank architectures cheaply, but their reliability varies across search spaces. We introduce CoRA-NAS (COarse Ranking + Anchor-residual), a two-stage framework combining a static ranking prior with low-cost learning…

  4. Hugging Face Daily Papers TIER_1 English(EN) ·

    CoRA-NAS：神经架构搜索的粗粒度排序和锚点残差细化

    Zero-cost proxies rank architectures cheaply, but their reliability varies across search spaces. We introduce CoRA-NAS (COarse Ranking + Anchor-residual), a two-stage framework combining a static ranking prior with low-cost learning-curve refinement. CoRA-Rank aggregates capacity…

相关实体

相关话题