English
Related papers

Related papers: Improved Catoni-Type Confidence Sequences for Esti…

200 papers

Central limit theorems (CLTs) for high-dimensional random vectors with dimension possibly growing with the sample size have received a lot of attention in the recent times. Chernozhukov et al. (2017) proved a Berry--Esseen type result for…

Statistics Theory · Mathematics 2019-06-26 Arun Kumar Kuchibhotla , Somabha Mukherjee , Debapratim Banerjee

Many inference problems, such as sequential decision problems like A/B testing, adaptive sampling schemes like bandit selection, are often online in nature. The fundamental problem for online inference is to provide a sequence of confidence…

Statistics Theory · Mathematics 2021-06-07 Arun Kumar Kuchibhotla , Qinqing Zheng

We study sequential mean estimation in $\mathbb{R}^d$. In particular, we derive time-uniform confidence spheres -- confidence sphere sequences (CSSs) -- which contain the mean of random vectors with high probability simultaneously across…

Statistics Theory · Mathematics 2025-05-16 Ben Chugg , Hongjian Wang , Aaditya Ramdas

We address the classical problem of constructing confidence intervals (CIs) for the mean of a distribution, given \(N\) i.i.d. samples, such that the CI contains the true mean with probability at least \(1 - \delta\), where \(\delta \in…

Statistics Theory · Mathematics 2026-04-02 Vikas Deep , Achal Bassamboo , Sandeep Juneja

In this paper, we study a stochastic strongly convex optimization problem and propose three classes of variable sample-size stochastic first-order methods including the standard stochastic gradient descent method, its accelerated variant,…

Optimization and Control · Mathematics 2024-05-08 Jinlong Lei , Uday V. Shanbhag

This paper revisits a fundamental problem in statistical inference from a non-asymptotic theoretical viewpoint $\unicode{x2013}$ the construction of confidence sets. We establish a finite-sample bound for the estimator, characterizing its…

Statistics Theory · Mathematics 2023-01-03 Lang Liu , Zaid Harchaoui

Estimating the maximum mean finds a variety of applications in practice. In this paper, we study estimation of the maximum mean using an upper confidence bound (UCB) approach where the sampling budget is adaptively allocated to one of the…

Statistics Theory · Mathematics 2024-08-09 Zhang Kun , Liu Guangwu , Shi Wen

The construction of confidence intervals for the mean of a bounded random variable is a classical problem in statistics with numerous applications in machine learning and virtually all scientific fields. In particular, obtaining the…

Machine Learning · Computer Science 2025-11-12 Václav Voráček , Francesco Orabona

We propose a finite-size scaling analysis of binary stochastic processes $X(t)\in \{0,1\}$ based on the second moment correlation length $\xi$ for the autocorrelation function $C(t)$. The purpose is to clarify the critical properties and…

Statistical Mechanics · Physics 2015-06-12 Shintaro Mori , Masato Hisakado

In this paper an easy to implement method of stochastically weighing short and long memory linear processes is introduced. The method renders asymptotically exact size confidence intervals for the population mean which are significantly…

Methodology · Statistics 2019-01-15 Masoud M Nasari , Mohamedou Ould-Haye

The Cauchy-Schwarz (CS) divergence was developed by Pr\'{i}ncipe et al. in 2000. In this paper, we extend the classic CS divergence to quantify the closeness between two conditional distributions and show that the developed conditional CS…

Machine Learning · Computer Science 2025-03-18 Shujian Yu , Hongming Li , Sigurd Løkse , Robert Jenssen , José C. Príncipe

Concentration inequalities for the sample mean, like those due to Bernstein, Hoeffding, and Bentkus, are valid for any sample size but overly conservative, yielding confidence intervals that are unnecessarily wide. The central limit theorem…

Probability · Mathematics 2025-12-23 Morgane Austern , Lester Mackey

This paper considers an empirical risk minimization problem under heavy-tailed settings, where data does not have finite variance, but only has $p$-th moment with $p \in (1,2)$. Instead of using estimation procedure based on truncated…

Machine Learning · Statistics 2023-09-08 Guanhua Fang , Ping Li , Gennady Samorodnitsky

We develop a general framework for conducting inference on the mean of dependent random variables given constraints on their dependency graph. We establish the consistency of an oracle variance estimator of the mean when the dependency…

Statistics Theory · Mathematics 2016-02-02 Peter M. Aronow , Forrest W. Crawford , José R. Zubizarreta

In this paper, we study the problem of distributed mean estimation with 1-bit communication constraints. We propose a mean estimator that is based on (randomized and sequentially-chosen) interval queries, whose 1-bit outcome indicates…

Machine Learning · Statistics 2026-04-07 Ivan Lau , Jonathan Scarlett

This paper investigates change point inference in high-dimensional time series. We begin by introducing a max-$L_2$-norm based test procedure, which demonstrates strong performance under dense alternatives. We then establish the asymptotic…

Methodology · Statistics 2025-11-04 Xiaoyi Wang , Jixuan Liu , Long Feng

Typical contextual bandit algorithms assume that the rewards at each round lie in some fixed range $[0, R]$, and their regret scales polynomially with this reward range $R$. However, many practical scenarios naturally involve heavy-tailed…

Machine Learning · Statistics 2025-02-05 Chenlu Ye , Yujia Jin , Alekh Agarwal , Tong Zhang

We consider estimation and inference on average treatment effects under unconfoundedness conditional on the realizations of the treatment variable and covariates. Given nonparametric smoothness and/or shape restrictions on the conditional…

Applications · Statistics 2022-10-04 Timothy B. Armstrong , Michal Kolesár

This paper addresses the statistical problem of estimating the infinite-norm deviation from the empirical mean to the distribution mean for high-dimensional distributions on $\{0,1\}^d$, potentially with $d=\infty$. Unlike traditional…

Statistics Theory · Mathematics 2024-02-21 Moïse Blanchard , Václav Voráček

We study problem-dependent rates, i.e., generalization errors that scale near-optimally with the variance, the effective loss, or the gradient norms evaluated at the "best hypothesis." We introduce a principled framework dubbed "uniform…

Machine Learning · Statistics 2020-12-25 Yunbei Xu , Assaf Zeevi