PulseAugur
中
实时 22:28:36
English(EN) $\sigma$Transfer: Uncertainty Transfer from Small to Large Networks under $\mu\mathrm{P}$

$\sigma$Transfer 实现小到大神经网络的高效不确定性迁移

研究人员开发了一种名为$\sigma$Transfer的方法,可以实现将预测不确定性信息从小型神经网络高效地迁移到显著更大的网络中。该技术利用最大更新参数化($\mu\text{P}$)来确保模型宽度增加时先验精度的稳定性,从而无需对大型模型进行昂贵的后验扫描。$\sigma$Transfer 已显示出显著的加速效果,在某些情况下高达5000倍,同时目标NLL的下降极小,并且还可以用于迁移与分布外检测和弃权相关的决策。 AI

影响 该方法可以显著加速大型神经网络中的不确定性估计,提高在分布外检测和决策制定等应用中的可靠性。

排序理由 这是一篇研究论文,详细介绍了一种新的神经网络不确定性迁移方法。[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 1 个来源。 我们如何撰写摘要 →

$\sigma$Transfer 实现小到大神经网络的高效不确定性迁移

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
这是一篇研究论文,详细介绍了一种新的神经网络不确定性迁移方法。[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, model release
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
2 days old
Coverage has settled into its steady-state source set.

完整方法见我们的编辑标准。

报道来源 [1]

  1. arXiv cs.LG TIER_1 English(EN) · Richard Bergna (University of Cambridge, Spotify), Fernando Ruiz Mazo (University of Cambridge), Nicol\`o Felicioni (Spotify), Jos\'e Miguel Hern\'andez-Lobato (University of Cambridge), Kamil Ciosek (Spotify) ·

    $\sigma$Transfer: 在 $\mu\mathrm{P}$ 下将不确定性从小型网络转移到大型网络

    arXiv:2610.11668v1 Announce Type: cross Abstract: Reliable predictive uncertainty in Laplace approximations depends critically on the prior precision, yet selecting it requires a posterior sweep that is prohibitively expensive for neural networks with billions of parameters. Unde…