English
Related papers

Related papers: A Finite-Sample Strong Converse for Binary Hypothe…

200 papers

Consider a binary statistical hypothesis testing problem, where $n$ independent and identically distributed random variables $Z^n$ are either distributed according to the null hypothesis $P$ or the alternative hypothesis $Q$, and only $P$…

Information Theory · Computer Science 2024-04-15 K. V. Harsha , Jithin Ravi , Tobias Koch

This paper is concerned with a Bayesian approach to testing hypotheses in statistical inverse problems. Based on the posterior distribution $\Pi \left(\cdot |Y = y\right)$, we want to infer whether a feature $\langle\varphi,…

Statistics Theory · Mathematics 2025-03-25 Remo Kretschmann , Frank Werner

We consider the sequential composite binary hypothesis testing problem in which one of the hypotheses is governed by a single distribution while the other is governed by a family of distributions whose parameters belong to a known set…

Information Theory · Computer Science 2022-03-30 Jiachun Pan , Yonglong Li , Vincent Y. F. Tan

This paper is twofold. In the first part, we present a refinement of the R\'enyi Entropy Power Inequality (EPI) recently obtained in \cite{BM16}. The proof largely follows the approach in \cite{DCT91} of employing Young's convolution…

Probability · Mathematics 2018-05-01 Jiange Li

A hypothesis testing algorithm is replicable if, when run on two different samples from the same distribution, it produces the same output with high probability. This notion, defined by by Impagliazzo, Lei, Pitassi, and Sorell [STOC'22],…

Data Structures and Algorithms · Computer Science 2025-09-05 Anders Aamand , Maryam Aliakbarpour , Justin Y. Chen , Shyam Narayanan , Sandeep Silwal

Score-based statistical models play an important role in modern machine learning, statistics, and signal processing. For hypothesis testing, a score-based hypothesis test is proposed in \cite{wu2022score}. We analyze the performance of this…

Signal Processing · Electrical Eng. & Systems 2024-02-06 Enmao Diao , Taposh Banerjee , Vahid Tarokh

We propose a new family of regularized R\'enyi divergences parametrized not only by the order $\alpha$ but also by a variational function space. These new objects are defined by taking the infimal convolution of the standard R\'enyi…

Machine Learning · Statistics 2023-02-16 Jeremiah Birrell , Yannis Pantazis , Paul Dupuis , Markos A. Katsoulakis , Luc Rey-Bellet

We consider a binary statistical hypothesis testing problem, where $n$ independent and identically distributed random variables $Z^n$ are either distributed according to the null hypothesis $P$ or the alternate hypothesis $Q$, and only $P$…

Information Theory · Computer Science 2022-05-12 K. V. Harsha , Jithin Ravi , Tobias Koch

Estimating divergences in a consistent way is of great importance in many machine learning tasks. Although this is a fundamental problem in nonparametric statistics, to the best of our knowledge there has been no finite sample exponential…

Information Theory · Computer Science 2016-03-30 Shashank Singh , Barnabás Póczos

We formulate a new information-theoretic principle--the shifted composition rule--which bounds the divergence (e.g., Kullback-Leibler or R\'enyi) between the laws of two stochastic processes via the introduction of auxiliary shifts. In this…

Probability · Mathematics 2023-11-27 Jason M. Altschuler , Sinho Chewi

Minimizing divergence measures under a constraint is an important problem. We derive a sufficient condition that binary divergence measures provide lower bounds for symmetric divergence measures under a given triangular discrimination or…

Information Theory · Computer Science 2022-11-11 Tomohiro Nishiyama

The two-sample hypothesis testing problem is studied for the challenging scenario of high dimensional data sets with small sample sizes. We show that the two-sample hypothesis testing problem can be posed as a one-class set classification…

Machine Learning · Statistics 2017-11-15 Hamed Masnadi-Shirazi

We study finite-sample inference for the trade-off function of two unknown probability distributions, the function that traces the optimal type I/type II error frontier in binary testing. Given samples from distributions $P$ and $Q$, we…

Statistics Theory · Mathematics 2026-05-12 Kaining Shi , Qiaosen Wang , Cong Ma

Given two sets of independent samples from unknown distributions $P$ and $Q$, a two-sample test decides whether to reject the null hypothesis that $P=Q$. Recent attention has focused on kernel two-sample tests as the test statistics are…

Machine Learning · Statistics 2018-05-22 Shengyu Zhu , Biao Chen , Zhitang Chen

A distributed binary hypothesis testing problem is studied with one observer and two decision centers. Achievable type-II error exponents are derived for testing against conditional independence when the observer communicates with the two…

Information Theory · Computer Science 2020-01-24 Sadaf Salehkalaibar , Michele Wigger , Roy Timo

Hypothesis testing in the linear regression model is a fundamental statistical problem. We consider linear regression in the high-dimensional regime where the number of parameters exceeds the number of samples ($p> n$). In order to make…

Statistics Theory · Mathematics 2019-09-24 Adel Javanmard , Jason D. Lee

Consider the problem of distributed binary hypothesis testing with two terminals, where the decision is made at one of them (the "receiver"). We study the exponent of the error probability of the second type. Previously, an achievable…

Information Theory · Computer Science 2025-08-26 Yuval Kochman , Ligong Wang

This paper establishes the exact strong converse exponent of the soft covering problem in the classical setting. This exponent characterizes the slowest achievable convergence speed of the total variation to one when a code of rate below…

Information Theory · Computer Science 2026-04-01 Xingyi He , S. Sandeep Pradhan , Andreas Winter

We consider binary classification problems with positive definite kernels and square loss, and study the convergence rates of stochastic gradient methods. We show that while the excess testing loss (squared loss) converges slowly to zero as…

Machine Learning · Computer Science 2018-11-21 Loucas Pillaud-Vivien , Alessandro Rudi , Francis Bach

R\'enyi divergence is related to R\'enyi entropy much like information divergence (also called Kullback-Leibler divergence or relative entropy) is related to Shannon's entropy, and comes up in many settings. It was introduced by R\'enyi as…

Information Theory · Computer Science 2010-05-28 Tim van Erven , Peter Harremoës