PulseAugur
实时 10:46:56
English(EN) MMD-Balls as Credal Sets: A PAC-Bayesian Framework for Epistemic Uncertainty in Test-Time Adaptation

新的 PAC-贝叶斯框架量化测试时自适应中的不确定性

研究人员开发了一个 PAC-贝叶斯框架,用于量化测试时自适应 (TTA) 方法中的认知不确定性。该框架使用源分布和目标分布之间的最大均值差异 (MMD) 来推导泛化界。通过将 MMD-balls 解释为 credal sets,该方法将认知不确定性与偶然不确定性分开,提供了一种有原则的方法来决定何时自适应是有益的。 AI

影响 为理解和量化模型适应新数据分布中的不确定性提供了理论基础。

排序理由 该集群包含一篇详细介绍机器学习新理论框架的学术论文。

在 arXiv stat.ML 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →

报道来源 [2]

  1. arXiv stat.ML TIER_1 English(EN) · Ahanaf Hasan Ariq ·

    MMD-Balls as Credal Sets: A PAC-Bayesian Framework for Epistemic Uncertainty in Test-Time Adaptation

    arXiv:2605.21783v1 Announce Type: cross Abstract: Test-time adaptation (TTA) methods improve model performance under distribution shift but lack formal guarantees connecting shift magnitude to prediction reliability. We develop a PAC-Bayesian framework yielding generalization bou…

  2. arXiv stat.ML TIER_1 English(EN) · Ahanaf Hasan Ariq ·

    MMD-Balls as Credal Sets: A PAC-Bayesian Framework for Epistemic Uncertainty in Test-Time Adaptation

    Test-time adaptation (TTA) methods improve model performance under distribution shift but lack formal guarantees connecting shift magnitude to prediction reliability. We develop a PAC-Bayesian framework yielding generalization bounds explicitly parameterized by the maximum mean d…