中文
相关论文

相关论文: The Geometric Median and Applications to Robust Me…

200 篇论文

There are several applications of stochastic optimization where one can benefit from a robust estimate of the gradient. For example, domains such as distributed learning with corrupted nodes, the presence of large outliers in the training…

机器学习 · 统计学 2025-10-30 Fabian Schaipp , Guillaume Garrigos , Umut Simsekli , Robert Gower

Motivated by the widely used geometric median-of-means estimator in machine learning, this paper studies statistical inference for ultrahigh dimensionality location parameter based on the sample spatial median under a general multivariate…

统计方法学 · 统计学 2023-01-10 Guanghui Cheng , Liuhua Peng , Changliang Zou

In this paper, we define the geometric median of a probability measure on a Riemannian manifold, give its characterization and a natural condition to ensure its uniqueness. In order to calculate the median in practical cases, we also…

微分几何 · 数学 2019-02-20 Le Yang

Robust statistics aims to compute quantities to represent data where a fraction of it may be arbitrarily corrupted. The most essential statistic is the mean, and in recent years, there has been a flurry of theoretical advancement for…

机器学习 · 统计学 2025-02-18 Cullen Anderson , Jeff M. Phillips

We study the problem of mean estimation for high-dimensional distributions, assuming access to a statistical query oracle for the distribution. For a normed space $X = (\mathbb{R}^d, \|\cdot\|_X)$ and a distribution supported on vectors $x…

数据结构与算法 · 计算机科学 2019-02-08 Jerry Li , Aleksandar Nikolov , Ilya Razenshteyn , Erik Waingarten

There are numerous examples in different research fields where the use of the geometric mean is more appropriate than the arithmetic mean. However, the geometric mean has a serious limitation in comparison with the arithmetic mean. Means…

应用统计 · 统计学 2019-04-05 Roberto de la Cruz , Jan-Ulrich Kreft

Robust estimators, like the median of a point set, are important for data analysis in the presence of outliers. We study robust estimators for locationally uncertain points with discrete distributions. That is, each point in a data set has…

离散数学 · 计算机科学 2018-03-14 Kevin Buchin , Jeff M. Phillips , Pingfan Tang

Estimating the mean of a random vector from i.i.d. data has received considerable attention, and the optimal accuracy one may achieve with a given confidence is fairly well understood by now. When the data take values in more general metric…

统计理论 · 数学 2025-09-18 Daniel Bartl , Gabor Lugosi , Roberto Imbuzeiro Oliveira , Zoraida F. Rico

We study the fundamental problem of high-dimensional mean estimation in a robust model where a constant fraction of the samples are adversarially corrupted. Recent work gave the first polynomial time algorithms for this problem with…

机器学习 · 计算机科学 2018-11-26 Yu Cheng , Ilias Diakonikolas , Rong Ge

We study the problem of robustly estimating the mean of a $d$-dimensional distribution given $N$ examples, where most coordinates of every example may be missing and $\varepsilon N$ examples may be arbitrarily corrupted. Assuming each…

数据结构与算法 · 计算机科学 2021-05-04 Lunjia Hu , Omer Reingold

As the most fundamental problem in statistics, robust location estimation has many prominent solutions, such as the trimmed mean, Winsorized mean, Hodges Lehmann estimator, Huber M estimator, and median of means. Recent studies suggest that…

统计理论 · 数学 2024-09-12 Li Tuobang

Robustness in terms of outliers is an important topic and has been formally studied for a variety of problems in machine learning and computer vision. Generalized median computation is a special instance of consensus learning and a common…

机器学习 · 计算机科学 2025-03-10 Andreas Nienkötter , Sandro Vega-Pons , Xiaoyi Jiang

In data-driven learning and inference tasks, the high cost of acquiring samples from the target distribution often limits performance. A common strategy to mitigate this challenge is to augment the limited target samples with data from a…

统计理论 · 数学 2025-02-06 Barron Han , Danil Akhtiamov , Reza Ghane , Babak Hassibi

The coordinate-wise median is a classic and most well-studied strategy-proof mechanism in social choice and facility location scenarios. Surprisingly, there is no systematic study of its approximation ratio in $d$-dimensional spaces. The…

计算机科学与博弈论 · 计算机科学 2025-02-14 Nick Gravin , Jianhao Jia

The standardized mean difference (SMD) is a widely used measure of effect size, particularly common in psychology, clinical trials, and meta-analysis involving continuous outcomes. Traditionally, under the equal variance assumption, the SMD…

统计方法学 · 统计学 2025-06-05 Jiandong Shi , Xiaochen Zhang , Lu Lin , Hiu Yee Kwan , Tiejun Tong

In the paper the maximum and the minimum of the ratio of the difference of the arithmetic mean and the geometric mean, and the difference of the power mean and the geometric mean of $n$ variables, are studied. A new optimization argument…

经典分析与常微分方程 · 数学 2025-08-26 Yagub Aliyev

In this paper, we study differentially private (DP) algorithms for computing the geometric median (GM) of a dataset: Given $n$ points, $x_1,\dots,x_n$ in $\mathbb{R}^d$, the goal is to find a point $\theta$ that minimizes the sum of the…

机器学习 · 计算机科学 2024-06-12 Mahdi Haghifam , Thomas Steinke , Jonathan Ullman

We revisit the problem of estimating the mean of a real-valued distribution, presenting a novel estimator with sub-Gaussian convergence: intuitively, "our estimator, on any distribution, is as accurate as the sample mean is for the Gaussian…

统计理论 · 数学 2020-11-18 Jasper C. H. Lee , Paul Valiant

We study the problem of high-dimensional robust mean estimation in the presence of a constant fraction of adversarial outliers. A recent line of work has provided sophisticated polynomial-time algorithms for this problem with…

机器学习 · 计算机科学 2020-05-05 Yu Cheng , Ilias Diakonikolas , Rong Ge , Mahdi Soltanolkotabi

The purpose of the present paper is to establish explicit bounds on moderate deviation probabilities for a rather general class of geometric functionals enjoying the stabilization property, under Poisson input and the assumption of a…

概率论 · 数学 2015-03-17 Peter Eichelsbacher , Martin Raic , Tomasz Schreiber