arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2305.03215math.STmath.MGstat.TH
收藏

度量空间中的测地凸$M$-估计

Geodesically convex $M$-estimation in metric spaces

Victor-Emmanuel Brunel

AI总结:

该研究针对非线性空间上的测地凸$M$-估计展开,在极少假设下证明了其一致性与渐近正态性,拓展了欧几里得凸$M$-估计理论,也推广了非线性空间的极限定理,支持非光滑$M$-估计的稳健替代方案。

摘要:

我们研究非线性空间上测地凸$M$-估计的渐近性质。具体而言,我们证明了除代价函数的测地凸性外,在极少的假设条件下,即可获得统计推断中的基本性质——一致性和渐近正态性。我们的结果拓展了凸$M$-估计的欧几里得理论;也推广了非线性空间上本质上仅对重心(barycenters)已知的极限定理,使得可考虑通过非光滑$M$-估计过程定义的稳健替代方法。

英文摘要:

We study the asymptotic properties of geodesically convex $M$-estimation on non-linear spaces. Namely, we prove that under very minimal assumptions besides geodesic convexity of the cost function, one can obtain consistency and asymptotic normality, which are fundamental properties in statistical inference. Our results extend the Euclidean theory of convex $M$-estimation; They also generalize limit theorems on non-linear spaces which, essentially, were only known for barycenters, allowing to consider robust alternatives that are defined through non-smooth $M$-estimation procedures.

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。

↑