English(EN) On the tradeoff between robustness and geometric accuracy in adversarial training

新研究量化了分类器鲁棒性与准确性之间的权衡

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-19 04:00

本文严格证明了非参数二元分类中对抗性分类器的最优定量估计。它证明了在控制豪斯多夫距离（与贝叶斯分类器相比）测量的几何精度时，鲁棒分类器在准确性上的损失最多为 $O(\sqrt{\varepsilon})$ 或 $O(\varepsilon)$，具体取决于贝叶斯分类器的正则性。这些发现适用于欧几里得空间中由任何范数定义的对抗者，并且在无限和有限数据设置中都有效，这与先前认为在低复杂度假设类别中鲁棒性与准确性不兼容的工作形成对比。 AI

影响为鲁棒的AI系统提供了理论保证，可能指导更可靠的机器学习模型的开发。

排序理由学术论文，详细介绍了对抗性训练的理论发现。[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 →

本文如何被排名

Signal score: 14 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 学术论文，详细介绍了对抗性训练的理论发现。[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, safety; 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: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.LG TIER_1 English(EN) · Rachel Morris, Ryan Murray, Kerrek Stinson · 2026-10-19 04:00

对抗性训练中鲁棒性与几何精度之间的权衡

arXiv:2610.22955v1 Announce Type: new Abstract: For non-parametric binary classification in the presence of an adversary, we prove an optimal quantitative estimate for adversarial classifiers controlling geometric accuracy, as measured by the Hausdorff distance to the Bayes class…

本文如何被排名

报道来源 [1]

对抗性训练中鲁棒性与几何精度之间的权衡

相关实体

相关话题