PulseAugur
中
实时 11:09:44
English(EN) Probe-Space Preconditioning for Fast and Stable Zero-Order Training

研究人员探索自适应优化器中的负预处理指数

作者 PulseAugur 编辑部 · [2 个来源] ·

研究人员调查了自适应优化器中负预处理指数的影响，特别是检查了它们与全局学习率的相互作用。通过在四个不同环境中的对照研究，他们发现最优指数几乎线性地随着学习率的对数而减小。这表明负指数并非普遍最优，而是由学习率和预处理的联合作用产生的状态，尤其是在较大的步长下。该研究还强调了模型选择中的一个冲突，即源域验证偏好与最大化对环境变化的鲁棒性的预处理状态不同。 AI

影响 这项研究可能为机器学习模型带来更强大、更具泛化能力的自适应优化器。

排序理由 该集群包含一篇发表在 arXiv 上的研究论文，详细介绍了对自适应优化器的研究。[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 2 个来源。 我们如何撰写摘要 →

研究人员探索自适应优化器中的负预处理指数

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
该集群包含一篇发表在 arXiv 上的研究论文，详细介绍了对自适应优化器的研究。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
2 independent sources
Multiple independent publishers reporting the same story raises confidence that it's real and newsworthy.
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
9 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.
Coverage growth since scoring
+1 source(s) since last score
New sources have picked up this story since our last re-score. Score will update on the next scoring pass.

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) · Francois Chaubard, Mykel J. Kochenderfer, Chris R\'e ·

    Probe-Space Preconditioning for Fast and Stable Zero-Order Training

    arXiv:2609.38095v1 Announce Type: new Abstract: Backpropagation (BP) dominates deep learning but imposes a massive memory tax. For example, training OPT-30B with Adam requires $\approx$ 600GB of GPU memory (assuming batch size 8 and sequence length 2048). Alternatively, zero-orde…

  2. arXiv cs.LG TIER_1 English(EN) · Gongyue Zhang, Honghai Liu ·

    当预训练指数变为负数时：学习率耦合与跨环境泛化

    arXiv:2609.30271v1 Announce Type: new Abstract: Adaptive optimizers are commonly parameterized by a fixed power of the second-moment estimate. Existing partially adaptive methods study exponents between momentum-like updates and the standard Adam square root, while the interactio…

相关实体

相关话题