English
Related papers

Related papers: Universal Neyman-Pearson Classification with a Kno…

200 papers

The classical binary hypothesis testing problem is revisited. We notice that when one of the hypotheses is composite, there is an inherent difficulty in defining an optimality criterion that is both informative and well-justified. For…

Statistics Theory · Mathematics 2021-03-29 Michael Bell , Yuval Kochman

Consider the problem of binary hypothesis testing. Given $Z$ coming from either $\mathbb P^{\otimes m}$ or $\mathbb Q^{\otimes m}$, to decide between the two with small probability of error it is sufficient, and in many cases necessary, to…

Statistics Theory · Mathematics 2024-03-11 Patrik Róbert Gerber , Yury Polyanskiy

Everybody writes that ROC curves, a very common tool in binary classification problems, should be optimal, and in particular concave, non-decreasing and above the 45-degree line. Everybody uses ROC curves, theoretical and especially…

Methodology · Statistics 2019-08-01 Lidia Sacchetto , Mauro Gasparini

The task of the binary classification problem is to determine which of two distributions has generated a length-$n$ test sequence. The two distributions are unknown; two training sequences of length $N$, one from each distribution, are…

Information Theory · Computer Science 2016-04-18 Dayu Huang , Sean Meyn

We consider the problem of Neyman-Pearson classification which models unbalanced classification settings where error w.r.t. a distribution $\mu_1$ is to be minimized subject to low error w.r.t. a different distribution $\mu_0$. Given a…

Machine Learning · Computer Science 2024-02-16 Mohammadreza M. Kalan , Samory Kpotufe

For the universal hypothesis testing problem, where the goal is to decide between the known null hypothesis distribution and some other unknown distribution, Hoeffding proposed a universal test in the nineteen sixties. Hoeffding's universal…

Information Theory · Computer Science 2016-11-15 Jayakrishnan Unnikrishnan , Dayu Huang , Sean Meyn , Amit Surana , Venugopal Veeravalli

Outlier hypothesis testing is studied in a universal setting. Multiple sequences of observations are collected, a small subset of which are outliers. A sequence is considered an outlier if the observations in that sequence are distributed…

Information Theory · Computer Science 2014-04-02 Yun Li , Sirin Nitinawarat , Venugopal V. Veeravalli

The law of total probability may be deployed in binary classification exercises to estimate the unconditional class probabilities if the class proportions in the training set are not representative of the population class proportions. We…

Probability · Mathematics 2014-02-17 Dirk Tasche

We consider pairs of finite-length individual sequences that are realizations of unknown, finite alphabet, stationary sources in a clas M of sources with vanishing memory (e.g. stationary Markov sources). The task of a universal classifier…

Information Theory · Computer Science 2011-11-08 Jacob Ziv

Motivated by real-world machine learning applications, we analyze approximations to the non-asymptotic fundamental limits of statistical classification. In the binary version of this problem, given two training sequences generated according…

Information Theory · Computer Science 2018-12-07 Lin Zhou , Vincent Y. F. Tan , Mehul Motani

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

We consider a problem of simple hypothesis testing using a randomized test via a tunable loss function proposed by Liao \textit{et al}. In this problem, we derive results that correspond to the Neyman--Pearson lemma, the Chernoff--Stein…

Information Theory · Computer Science 2022-08-30 Akira Kamatsuka

We provide a complete theory of optimal universal rates for binary classification in the agnostic setting. This extends the realizable-case theory of Bousquet, Hanneke, Moran, van Handel, and Yehudayoff (2021) by removing the realizability…

Machine Learning · Computer Science 2026-01-30 Steve Hanneke , Shay Moran

We study the problem of mismatched binary hypothesis testing between i.i.d. distributions. We analyze the tradeoff between the pairwise error probability exponents when the actual distributions generating the observation are different from…

Information Theory · Computer Science 2022-04-28 Parham Boroumand , Albert Guillén i Fàbregas

Universal outlier hypothesis testing refers to a hypothesis testing problem where one observes a large number of length-$n$ sequences -- the majority of which are distributed according to the typical distribution $\pi$ and a small number…

Information Theory · Computer Science 2026-01-05 Bernhard C. Geiger , Tobias Koch , Josipa Mihaljević , Maximilian Toller

Selective classification is a powerful tool for automated decision-making in high-risk scenarios, allowing classifiers to act only when confident and abstain when uncertainty is high. Given a target accuracy, our goal is to minimize…

Statistics Theory · Mathematics 2025-10-28 Mohamed Ndaoud , Peter Radchenko , Bradley Rava

Asymmetric binary classification problems, in which the type I and II errors have unequal severity, are ubiquitous in real-world applications. To handle such asymmetry, researchers have developed the cost-sensitive and Neyman-Pearson…

Machine Learning · Statistics 2021-01-01 Wei Vivian Li , Xin Tong , Jingyi Jessica Li

Universal outlier hypothesis testing is studied in a sequential setting. Multiple observation sequences are collected, a small subset of which are outliers. A sequence is considered an outlier if the observations in that sequence are…

Statistics Theory · Mathematics 2014-11-27 Yun Li , Sirin Nitinawarat , Venugopal V. Veeravalli

A critical barrier to learning an accurate decision rule for outlier detection is the scarcity of outlier data. As such, practitioners often turn to the use of similar but imperfect outlier data from which they might transfer information to…

Machine Learning · Computer Science 2023-10-10 Mohammadreza M. Kalan , Samory Kpotufe

This paper introduces the generalized Hausman test as a novel method for detecting non-normality of the latent variable distribution of unidimensional Item Response Theory (IRT) models for binary data. The test utilizes the pairwise maximum…

Methodology · Statistics 2024-02-14 Lucia Guastadisegni , Silvia Cagnone , Irini Moustaki , Vassilis Vasdekis