English
Related papers

Related papers: Testing Dependency of Unlabeled Databases

200 papers

Given $n$ observations from two balanced classes, consider the task of labeling an additional $m$ inputs that are known to all belong to \emph{one} of the two classes. Special cases of this problem are well-known: with complete knowledge of…

Machine Learning · Statistics 2023-11-27 Patrik Róbert Gerber , Tianze Jiang , Yury Polyanskiy , Rui Sun

We study the problem of hypothesis testing between two discrete distributions, where we only have access to samples after the action of a known reversible Markov chain, playing the role of noise. We derive instance-dependent minimax rates…

Statistics Theory · Mathematics 2018-08-15 Quentin Berthet , Varun Kanade

In this paper we consider the uniformity testing problem for high-dimensional discrete distributions (multinomials) under sparse alternatives. More precisely, we derive sharp detection thresholds for testing, based on $n$ samples, whether a…

Statistics Theory · Mathematics 2022-02-17 Bhaswar B. Bhattacharya , Rajarshi Mukherjee

We consider the problem of testing whether pairs of univariate random variables are associated. Few tests of independence exist that are consistent against all dependent alternatives and are distribution free. We propose novel tests that…

Methodology · Statistics 2014-12-09 Ruth Heller , Yair Heller , Shachar Kaufman , Malka Gorfine

A number of applications require two-sample testing on ranked preference data. For instance, in crowdsourcing, there is a long-standing question of whether pairwise comparison data provided by people is distributed similar to…

Machine Learning · Statistics 2020-11-20 Charvi Rastogi , Sivaraman Balakrishnan , Nihar B. Shah , Aarti Singh

A popular approach for testing if two univariate random variables are statistically independent consists of partitioning the sample space into bins, and evaluating a test statistic on the binned data. The partition size matters, and the…

Methodology · Statistics 2016-04-28 Ruth Heller , Yair Heller , Shachar Kaufman , Barak Brill , Malka Gorfine

Binary hypothesis testing under the Neyman-Pearson formalism is a statistical inference framework for distinguishing data generated by two different source distributions. Privacy restrictions may require the curator of the data or the data…

Information Theory · Computer Science 2016-07-05 Jiachun Liao , Lalitha Sankar , Vincent Y. F. Tan , Flavio P. Calmon

Testing whether a probability distribution is compatible with a given Bayesian network is a fundamental task in the field of causal inference, where Bayesian networks model causal relations. Here we consider the class of causal structures…

Machine Learning · Statistics 2020-09-04 Aditya Kela , Kai von Prillwitz , Johan Aberg , Rafael Chaves , David Gross

This paper introduces a statistical test inferring whether a variable allows separating two classes by means of a single critical value. Its test statistic is the prediction error of a nonparametric threshold classifier. While this approach…

Methodology · Statistics 2017-07-17 Fabian Schroeder

In many supervised learning tasks, the entities to be labeled are related to each other in complex ways and their labels are not independent. For example, in hypertext classification, the labels of linked pages are highly correlated. A…

Machine Learning · Computer Science 2013-01-07 Ben Taskar , Pieter Abbeel , Daphne Koller

We revisit the classical broken sample problem: Two samples of i.i.d. data points $\mathbf{X}=\{X_1,\cdots, X_n\}$ and $\mathbf{Y}=\{Y_1,\cdots,Y_m\}$ are observed without correspondence with $m\leq n$. Under the null hypothesis,…

Statistics Theory · Mathematics 2025-03-20 Simiao Jiao , Yihong Wu , Jiaming Xu

A popular framework for false discovery control is the random effects model in which the null hypotheses are assumed to be independent. This paper generalizes the random effects model to a conditional dependence model which allows…

Statistics Theory · Mathematics 2008-12-18 Wei Biao Wu

Testing mutual independence for high-dimensional observations is a fundamental statistical challenge. Popular tests based on linear and simple rank correlations are known to be incapable of detecting non-linear, non-monotone relationships,…

Statistics Theory · Mathematics 2020-02-06 Mathias Drton , Fang Han , Hongjian Shi

We introduce a test for the conditional independence of random variables $X$ and $Y$ given a random variable $Z$, specifically by sampling from the joint distribution $(X,Y,Z)$, binning the support of the distribution of $Z$, and conducting…

Statistics Theory · Mathematics 2024-02-05 Andrew Warren

We consider nonparametric or universal sequential hypothesis testing problem when the distribution under the null hypothesis is fully known but the alternate hypothesis corresponds to some other unknown distribution. These algorithms are…

Information Theory · Computer Science 2013-08-30 Jithin K. Sreedharan , Vinod Sharma

Diffusion language models (DLMs) have recently emerged as a promising alternative to autoregressive (AR) approaches, enabling parallel token generation beyond a rigid left-to-right order. Despite growing empirical success, the theoretical…

Machine Learning · Computer Science 2026-02-24 Yunxiao Zhao , Changxiao Cai

Sampling algorithms play a pivotal role in probabilistic AI. However, verifying if a sampler program indeed samples from the claimed distribution is a notoriously hard problem. Provably correct testers like Barbarik, Teq, Flash, CubeProbe…

Data Structures and Algorithms · Computer Science 2025-12-09 Rishiraj Bhattacharyya , Sourav Chakraborty , Yash Pote , Uddalok Sarkar , Sayantan Sen

In this paper, we introduce a ${\mathcal L}_2$ type test for testing mutual independence and banded dependence structure for high dimensional data. The test is constructed based on the pairwise distance covariance and it accounts for the…

Methodology · Statistics 2017-09-20 Shun Yao , Xianyang Zhang , Xiaofeng Shao

One important obstacle in applying Dempster-Shafer Theory (DST) is its relationship to frequencies. In particular, there exist serious difficulties in finding factorizations of belief functions from data. In probability theory…

Artificial Intelligence · Computer Science 2018-12-17 Andrzej Matuszewski , Mieczysław A. Kłopotek

Given an imperfect predictor, we exploit additional features at test time to improve the predictions made, without retraining and without knowledge of the prediction function. This scenario arises if training labels or data are proprietary,…

Machine Learning · Computer Science 2021-11-05 Kwang In Kim , James Tompkin