改进了贝塔与狄利克雷分布的尾部概率上界,提升精度。
Sharper Perturbed-Kullback-Leibler Exponential Tail Bounds for Beta and Dirichlet Distributions
- 通过引入扰动项η,使贝塔分布均值更贴近零点,优化KL散度上界。
- 新界比已有结果更紧致,在相同置信水平下误差更小。
- 方法可推广至狄利克雷分布和狄利克雷过程,适用性更广。
本文提出对贝塔分布的指数尾部上界进行改进,超越了文献[15]的结果。我们将其原上界解释为标准Kullback-Leibler(KL)散度形式,并引入一个特定扰动η,将贝塔分布的均值在KL边界中向零方向移动。我们的贡献在于证明可采用更大的扰动值,从而进一步收紧上界。随后,该结果被拓展至狄利克雷分布及狄利克雷过程(DPs),增强了理论工具在高维概率建模中的应用潜力。
原文摘要 · Abstract (English)
This paper presents an improved exponential tail bound for Beta distributions, refining a result in [15]. This improvement is achieved by interpreting their bound as a regular Kullback-Leibler (KL) divergence one, while introducing a specific perturbation $η$ that shifts the mean of the Beta distribution closer to zero within the KL bound. Our contribution is to show that a larger perturbation can be chosen, thereby tightening the bound. We then extend this result from the Beta distribution to Dirichlet distributions and Dirichlet processes (DPs).
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品;中文卡片由大模型生成,请以原文为准。