PulseAugur
实时 06:03:18
English(EN) Beyond Global Divergences: A Local-Mass Perspective on Bayesian Inference

新工具分析贝叶斯推断中的局部质量行为

本文介绍了新的数学工具,即质量指数(Mass Index)和正则化扩展KL(RE-KL),用于分析贝叶斯推断中的局部质量行为。这些工具超越了KL散度(KL divergence)和ELBO等传统的全局目标,以表征贝叶斯更新如何影响局部质量。该研究为理解局部质量行为提供了理论框架,并包含实验说明。 AI

影响 引入了用于分析贝叶斯推断的新颖理论工具,可能影响机器学习和概率建模的未来研究。

排序理由 该集群包含一篇发表在arXiv上的研究论文,详细介绍了用于贝叶斯推断的新理论工具。

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 →

新工具分析贝叶斯推断中的局部质量行为

报道来源 [2]

  1. arXiv cs.LG TIER_1 English(EN) · Sarat Moka ·

    超越全球分歧:贝叶斯推断的局部质量视角

    Global objectives, such as KL divergence and ELBO, are widely used in Bayesian inference for measuring distributional discrepancy. This paper studies their local-mass behaviour that is not directly captured by such objectives. We introduce and use two mathematical tools: (1) Mass…

  2. arXiv stat.ML TIER_1 English(EN) · Hanli Xu, Fengxiang He, Sarat Moka ·

    Beyond Global Divergences: A Local-Mass Perspective on Bayesian Inference

    arXiv:2606.27090v1 Announce Type: new Abstract: Global objectives, such as KL divergence and ELBO, are widely used in Bayesian inference for measuring distributional discrepancy. This paper studies their local-mass behaviour that is not directly captured by such objectives. We in…