English
Related papers

Related papers: Sample Complexity Result for Multi-category Classi…

200 papers

We develop new approaches in multi-class settings for constructing proper scoring rules and hinge-like losses and establishing corresponding regret bounds with respect to the zero-one or cost-weighted classification loss. Our construction…

Statistics Theory · Mathematics 2021-05-18 Zhiqiang Tan , Xinwei Zhang

For the binary prevalence quantification problem under prior probability shift, we determine the asymptotic variance of the maximum likelihood estimator. We find that it is a function of the Brier score for the regression of the class label…

Machine Learning · Statistics 2021-09-23 Dirk Tasche

Margin-based classifiers have been popular in both machine learning and statistics for classification problems. Since a large number of classifiers are available, one natural question is which type of classifiers should be used given a…

Machine Learning · Statistics 2021-10-19 Hanwen Huang , Qinglong Yang

This paper extends standard results from learning theory with independent data to sequences of dependent data. Contrary to most of the literature, we do not rely on mixing arguments or sequential measures of complexity and derive uniform…

Machine Learning · Computer Science 2023-03-22 Fabien Lauer

Universal dimensionless quantities, such as Binder ratios and wrapping probabilities, play an important role in the study of critical phenomena. We study the finite-size scaling behavior of the wrapping probability for the Potts model in…

Statistical Mechanics · Physics 2015-07-14 Hao Hu , Youjin Deng

Machine-generated probability predictions are essential in modern classification tasks such as image classification. A model is well calibrated when its predicted probabilities correspond to observed event frequencies. Despite the need for…

Machine Learning · Statistics 2026-02-24 Amy Vennos , Xin Xing , Christopher T. Franck

We consider the problem of setting confidence intervals on a parameter of interest from the maximum-likelihood fit of a physics model to a binned data set with a large number of bins, large event-counts per bin, and in the presence of…

Data Analysis, Statistics and Probability · Physics 2026-02-09 Cristina-Andreea Alexe , Joshua Bendavid , Lorenzo Bianchini , Davide Bruschini

We study the sample complexity of learning a uniform approximation of an $n$-dimensional cumulative distribution function (CDF) within an error $\epsilon > 0$, when observations are restricted to a minimal one-bit feedback. This serves as a…

Machine Learning · Computer Science 2026-05-12 Matteo Castiglioni , Anna Lunghi , Alberto Marchesi

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

Binary classification from positive-only samples is a variant of PAC learning where the learner receives i.i.d. positive samples and aims to learn a classifier with low error. Previous work by Natarajan, Gereb-Graus, and Shvaytser…

Machine Learning · Statistics 2026-05-13 Jane H. Lee , Anay Mehrotra , Manolis Zampetakis

When dealing with imbalanced classification data, reweighting the loss function is a standard procedure allowing to equilibrate between the true positive and true negative rates within the risk measure. Despite significant theoretical work…

Machine Learning · Statistics 2024-04-17 Anass Aghbalou , François Portier , Anne Sabourin

Overconfidence and underconfidence in machine learning classifiers is measured by calibration: the degree to which the probabilities predicted for each class match the accuracy of the classifier on that prediction. How one measures…

Machine Learning · Computer Science 2020-08-11 Jeremy Nixon , Mike Dusenberry , Ghassen Jerfel , Timothy Nguyen , Jeremiah Liu , Linchuan Zhang , Dustin Tran

Cross-validation techniques for risk estimation and model selection are widely used in statistics and machine learning. However, the understanding of the theoretical properties of learning via model selection with cross-validation risk…

Machine Learning · Statistics 2024-05-27 Diego Marcondes , Cláudia Peixoto

The vast majority of statistical theory on binary classification characterizes performance in terms of accuracy. However, accuracy is known in many cases to poorly reflect the practical consequences of classification error, most famously in…

Statistics Theory · Mathematics 2022-09-27 Shashank Singh , Justin Khim

We present novel reductions from sample compression schemes in multiclass classification, regression, and adversarially robust learning settings to binary sample compression schemes. Assuming we have a compression scheme for binary classes…

Machine Learning · Computer Science 2025-04-09 Idan Attias , Steve Hanneke , Arvind Ramaswami

Input variables in numerical models are often subject to several levels of uncertainty, usually modeled by probability distributions. In the context of uncertainty quantification applied to these models, studying the robustness of output…

A large set of signals can sometimes be described sparsely using a dictionary, that is, every element can be represented as a linear combination of few elements from the dictionary. Algorithms for various signal processing applications,…

Machine Learning · Statistics 2013-02-06 Daniel Vainsencher , Shie Mannor , Alfred M. Bruckstein

We study the statistical complexity of estimating partition functions given sample access to a proposal distribution and an unnormalized density ratio for a target distribution. While partition function estimation is a classical problem,…

Machine Learning · Statistics 2026-03-02 Adam Block , Abhishek Shetty

This work continues the study of the relationship between sample compression schemes and statistical learning, which has been mostly investigated within the framework of binary classification. The central theme of this work is establishing…

Machine Learning · Computer Science 2017-01-02 Ofir David , Shay Moran , Amir Yehudayoff

Recent works have investigated the sample complexity necessary for fair machine learning. The most advanced of such sample complexity bounds are developed by analyzing multicalibration uniform convergence for a given predictor class. We…

Machine Learning · Computer Science 2022-02-10 Harrison Rosenberg , Robi Bhattacharjee , Kassem Fawaz , Somesh Jha