English(EN) Linear Mode Connectivity under Data Shifts for Deep Ensembles of Image Classifiers

深度集成在数据偏移下表现出线性模式连通性

作者 PulseAugur 编辑部 · [1 个来源] · 2026-06-19 04:00

研究人员调查了深度学习中线性模式连通性（LMC）的现象，特别是它如何受到图像分类器集成中数据偏移的影响。研究表明，数据偏移可以被视为一种随机梯度噪声，可以通过使用更小的学习率和更大的批量大小来缓解。这些参数会影响模型收敛到损失景观的相似或不同区域，从而影响训练效率和集成多样性之间的权衡。 AI

影响为深度学习模型的训练稳定性和泛化能力提供了见解，可能改进集成方法。

排序理由这是一篇发表在arXiv上的研究论文，详细介绍了深度学习现象的实验结果。[lever_c_demoted from research: ic=1 ai=1.0]

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

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; 这是一篇发表在arXiv上的研究论文，详细介绍了深度学习现象的实验结果。[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: 110 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。

arXiv cs.LG TIER_1 English(EN) · C. Hepburn, T. Zielke, A. P. Raulf · 2026-06-19 04:00

深度集成图像分类器在数据偏移下的线性模式连通性

arXiv:2511.04514v2 Announce Type: replace Abstract: The phenomenon of linear mode connectivity (LMC) links several aspects of deep learning, including training stability under noisy stochastic gradients, the smoothness and generalization of local minima (basins), the similarity a…