English
Related papers

Related papers: Distribution-Free Rates in Neyman-Pearson Classifi…

200 papers

We study the Neyman-Pearson theory for convex expectations (convex risk measures) on $L^{\infty}(\mu)$. Without assuming that the level sets of penalty functions are weakly compact, a new approach different from the convex duality method is…

Probability · Mathematics 2019-12-30 Sun Chuanfeng , Ji Shaolin

In statistical learning theory, determining the sample complexity of realizable binary classification for VC classes was a long-standing open problem. The results of Simon and Hanneke established sharp upper bounds in this setting. However,…

Machine Learning · Computer Science 2023-04-19 Ishaq Aden-Ali , Yeshwanth Cherapanamjeri , Abhishek Shetty , Nikita Zhivotovskiy

This article provides, through theoretical analysis, an in-depth understanding of the classification performance of the empirical risk minimization framework, in both ridge-regularized and unregularized cases, when high dimensional data are…

Machine Learning · Statistics 2020-11-26 Xiaoyi Mai , Zhenyu Liao

In this paper, we investigate the problem of classifying feature vectors with mutually independent but non-identically distributed elements. First, we show the importance of this problem. Next, we propose a classifier and derive an…

Machine Learning · Computer Science 2021-09-01 Farzad Shahrivari , Nikola Zlatanov

Controlling the dispersion of a subset of decision variables in an optimization problem is crucial for enforcing fairness or load-balancing across a wide range of applications. Building on the well-known equivalence of finite-dimensional…

Optimization and Control · Mathematics 2026-05-15 Abhay Singh Bhadoriya , Deepjyoti Deka , Kaarthik Sundar

Learning a robust classifier from a few samples remains a key challenge in machine learning. A major thrust of research has been focused on developing $k$-nearest neighbor ($k$-NN) based algorithms combined with metric learning that…

Machine Learning · Statistics 2022-02-17 Shixiang Zhu , Liyan Xie , Minghe Zhang , Rui Gao , Yao Xie

We introduce an enumeration-free method based on mathematical programming to precisely characterize various properties such as fairness or sparsity within the set of "good models", known as Rashomon set. This approach is generically…

Machine Learning · Computer Science 2025-07-08 Lucas Langlade , Julien Ferry , Gabriel Laberge , Thibaut Vidal

One of the most popular class of tests for independence between two random variables is the general class of rank statistics which are invariant under permutations. This class contains Spearman's coefficient of rank correlation statistic,…

Computation · Statistics 2009-02-04 Ehab F. Abd-Elfattah

The Fundamental Theorem of PAC Learning asserts that learnability of a concept class $H$ is equivalent to the $\textit{uniform convergence}$ of empirical error in $H$ to its mean, or equivalently, to the problem of $\textit{density…

Machine Learning · Computer Science 2025-03-04 Max Hopkins , Daniel M. Kane , Shachar Lovett , Gaurav Mahajan

Feature selection aims to select the smallest subset of features for a specified level of performance. The optimal achievable classification performance on a feature subset is summarized by its Receiver Operating Curve (ROC). When infinite…

Machine Learning · Computer Science 2013-01-18 Frans Coetzee , Steve Lawrence , C. Lee Giles

We consider high-dimensional binary classification by sparse logistic regression. We propose a model/feature selection procedure based on penalized maximum likelihood with a complexity penalty on the model size and derive the non-asymptotic…

Statistics Theory · Mathematics 2018-11-20 Felix Abramovich , Vadim Grinshtein

In mathematical models of epidemic diffusion on networks based upon systems of differential equations, it is convenient to use the Heterogeneous Mean Field approximation (HMF) because it allows to write one single equation for all nodes of…

Physics and Society · Physics 2024-11-12 L. Di Lucchio , G. Modanese

Consider the problem where a statistician in a two-node system receives rate-limited information from a transmitter about marginal observations of a memoryless process generated from two possible distributions. Using its own observations,…

Information Theory · Computer Science 2017-03-02 Gil Katz , Pablo Piantanida , Mérouane Debbah

Algorithmic fairness has become a central concern in modern machine learning and AI applications. However, two pressing challenges remain: (1) The fairness guarantees of existing methods often rely on specific data distributional…

Methodology · Statistics 2026-05-14 Xiaotian Hou , Linjun Zhang

We study the problem of setting a price for a potential buyer with a valuation drawn from an unknown distribution $D$. The seller has "data"' about $D$ in the form of $m \ge 1$ i.i.d. samples, and the algorithmic challenge is to use these…

Computer Science and Game Theory · Computer Science 2015-02-12 Zhiyi Huang , Yishay Mansour , Tim Roughgarden

This paper develops a unified framework for asymptotically minimax robust hypothesis testing under distributional uncertainty, applicable to both Bayesian and Neyman--Pearson formulations (Type-I and Type-II). Uncertainty classes based on…

Statistics Theory · Mathematics 2026-02-10 Gökhan Gül

In high-dimensional data analysis, regularization methods pursuing sparsity and/or low rank have received a lot of attention recently. To provide a proper amount of shrinkage, it is typical to use a grid search and a model comparison…

Methodology · Statistics 2019-01-01 Yiyuan She , Hoang Tran

An "element-free" probability distribution is what remains of a probability distribution after we forget the elements to which the probabilities were assigned. These objects naturally arise in Bayesian statistics, in situations where…

Logic in Computer Science · Computer Science 2024-05-29 Victor Blanchi , Hugo Paquet

We study three notions of uncertainty quantification -- calibration, confidence intervals and prediction sets -- for binary classification in the distribution-free setting, that is without making any distributional assumptions on the data.…

Machine Learning · Statistics 2022-02-17 Chirag Gupta , Aleksandr Podkopaev , Aaditya Ramdas

This paper studies the problem of nonparametric estimation of a smooth function with data distributed across multiple machines. We assume an independent sample from a white noise model is collected at each machine, and an estimator of the…

Machine Learning · Statistics 2018-06-26 Yuancheng Zhu , John Lafferty