arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2402.08422math.STcs.LGstat.TH
收藏

无穷范数下的分布估计

Distribution Estimation under the Infinity Norm

Ben Gurion University(本古里安大学);Tel Aviv University(特拉维夫大学)

Aryeh Kontorovich, Amichai Painsky

AI总结:

本文提出了在 $\ell_\infty$ 范数下估计离散概率分布的新界限,通过创新 Chernoff 型不等式和经验 Bernstein 界限等技术,改进了最大似然估计器的收敛保证,并应用于选择性推断问题。

摘要:

我们提出了在 $\ell_\infty$ 范数下估计离散概率分布的新界限。这些界限在多种精确意义上近乎最优,包括一种实例最优性。我们对最大似然估计器的数据相关收敛保证显著改进了现有已知结果。我们运用并创新了多种技术,包括 Chernoff 型不等式和经验 Bernstein 界限。我们在合成和真实世界实验中展示了结果。最后,我们将提出的框架应用于一个基础的选择性推断问题,即估计样本中最频繁的概率。

英文摘要:

We present novel bounds for estimating discrete probability distributions under the $\ell_\infty$ norm. These are nearly optimal in various precise senses, including a kind of instance-optimality. Our data-dependent convergence guarantees for the maximum likelihood estimator significantly improve upon the currently known results. A variety of techniques are utilized and innovated upon, including Chernoff-type inequalities and empirical Bernstein bounds. We illustrate our results in synthetic and real-world experiments. Finally, we apply our proposed framework to a basic selective inference problem, where we estimate the most frequent probabilities in a sample.

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。

↑