通过密度比界定分布误差
Bounding distributional errors via density ratios
摘要：
我们提出了一些新的和明确的误差界的近似分布。近似误差由待近似的分布$Q$及其代理$P$的最大密度比来量化。这种非对称测量比全变差距离的范围信息量更大，并意味着该范围。显式近似问题包括超几何二项分布、二项分布泊松分布和贝塔分布Γ分布。在许多情况下，我们同时提供上界和（匹配的）下界。
英文摘要：
We present some new and explicit error bounds for the approximation of distributions. The approximation error is quantified by the maximal density ratio of the distribution $Q$ to be approximated and its proxy $P$. This non-symmetric measure is more informative than and implies bounds for the total variation distance. Explicit approximation problems include, among others, hypergeometric by binomial distributions, binomial by Poisson distributions, and beta by gamma distributions. In many cases we provide both upper and (matching) lower bounds.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
