English
Related papers

Related papers: Minimax optimal testing by classification

200 papers

Consider a two-class classification problem where the number of features is much larger than the sample size. The features are masked by Gaussian noise with mean zero and covariance matrix $\Sigma$, where the precision matrix…

Machine Learning · Statistics 2013-11-21 Yingying Fan , Jiashun Jin , Zhigang Yao

Learning the minimum/maximum mean among a finite set of distributions is a fundamental sub-task in planning, game tree search and reinforcement learning. We formalize this learning task as the problem of sequentially testing how the minimum…

Machine Learning · Statistics 2018-06-05 Emilie Kaufmann , Wouter Koolen , Aurelien Garivier

Prediction sets can wrap around any ML model to cover unknown test outcomes with a guaranteed probability. Yet, it remains unclear how to use them optimally for downstream decision-making. Here, we propose a decision-theoretic framework…

Machine Learning · Statistics 2026-02-10 Tao Wang , Edgar Dobriban

Optimization-based meta-learning offers a promising direction for few-shot learning that is essential for many real-world computer vision applications. However, learning from few samples introduces uncertainty, and quantifying model…

Computer Vision and Pattern Recognition · Computer Science 2022-03-25 Deep Pandey , Qi Yu

There exist a wide range of single number metrics for assessing performance of classification algorithms, including AUC and the F1-score (Wikipedia lists 17 such metrics, with 27 different names). In this article, I propose a new metric to…

Machine Learning · Computer Science 2023-11-21 David J. T. Sumpter

Nonparametric tests for equality of multivariate distributions are frequently desired in research. It is commonly required that test-procedures based on relatively small samples of vectors accurately control the corresponding Type I Error…

Methodology · Statistics 2021-01-14 Ablert Vexler , Gregory Gurevich , Li Zou

We consider the problem of testing a particular type of composite null hypothesis under a nonparametric multivariate regression model. For a given quadratic functional $Q$, the null hypothesis states that the regression function $f$…

Statistics Theory · Mathematics 2013-01-09 Laëtitia Comminges , Arnak Dalalyan

Practical problems with missing data are common, and statistical methods have been developed concerning the validity and/or efficiency of statistical procedures. On a central focus, there have been longstanding interests on the mechanism…

Methodology · Statistics 2020-03-26 Rui Duan , C. Jason Liang , Pamela Shaw , Cheng Yong Tang , Yong Chen

We consider the problem of finding an approximate solution to $\ell_1$ regression while only observing a small number of labels. Given an $n \times d$ unlabeled data matrix $X$, we must choose a small set of $m \ll n$ rows to observe the…

Machine Learning · Computer Science 2021-05-21 Aditya Parulekar , Advait Parulekar , Eric Price

We consider the problem of binary classification with abstention in the relatively less studied \emph{bounded-rate} setting. We begin by obtaining a characterization of the Bayes optimal classifier for an arbitrary input-label distribution…

Machine Learning · Computer Science 2019-05-24 Shubhanshu Shekhar , Mohammad Ghavamzadeh , Tara Javidi

We study the sample complexity of semi-supervised learning (SSL) and introduce new assumptions based on the mismatch between a mixture model learned from unlabeled data and the true mixture model induced by the (unknown) class conditional…

Machine Learning · Computer Science 2018-09-11 Chen Dan , Liu Leqi , Bryon Aragam , Pradeep Ravikumar , Eric P. Xing

We provide a means of computing and estimating the asymptotic distributions of statistics based on an outer minimization of an inner maximization. Such test statistics, which arise frequently in moment models, are of special interest in…

Econometrics · Economics 2024-04-17 Isaac Loh

In this paper, we propose a simple yet effective method to deal with the violation of the Closed-World Assumption for a classifier. Previous works tend to apply a threshold either on the classification scores or the loss function to reject…

Computer Vision and Pattern Recognition · Computer Science 2021-08-17 Saeed Bakhshi Germi , Esa Rahtu , Heikki Huttunen

We develop a worst-case analysis of aggregation of classifier ensembles for binary classification. The task of predicting to minimize error is formulated as a game played over a given set of unlabeled data (a transductive setting), where…

Machine Learning · Computer Science 2015-06-22 Akshay Balsubramani , Yoav Freund

We revisit the outlier hypothesis testing framework of Li \emph{et al.} (TIT 2014) and derive fundamental limits for the optimal test. In outlier hypothesis testing, one is given multiple observed sequences, where most sequences are…

Statistics Theory · Mathematics 2022-05-17 Lin Zhou , Yun Wei , Alfred Hero

We give the first efficient algorithm for learning halfspaces in the testable learning model recently defined by Rubinfeld and Vasilyan (2023). In this model, a learner certifies that the accuracy of its output hypothesis is near optimal…

Machine Learning · Computer Science 2023-03-14 Aravind Gollakota , Adam R. Klivans , Konstantinos Stavropoulos , Arsen Vasilyan

In classification tasks, softmax functions are ubiquitously used as output activations to produce predictive probabilities. Such outputs only capture aleatoric uncertainty. To capture epistemic uncertainty, approximate Gaussian inference…

Machine Learning · Computer Science 2026-02-12 Bálint Mucsányi , Nathaël Da Costa , Philipp Hennig

We develop a general framework for estimating the $L_\infty(\mathbb{T}^d)$ error for the approximation of multivariate periodic functions belonging to specific reproducing kernel Hilbert spaces (RHKS) using approximants that are…

Numerical Analysis · Mathematics 2019-09-06 Lutz Kämmerer

We investigate the problem of classification in the presence of unknown class-conditional label noise in which the labels observed by the learner have been corrupted with some unknown class dependent probability. In order to obtain finite…

Machine Learning · Statistics 2019-06-11 Henry W J Reeve , Ata Kaban

Learning exists in the context of data, yet notions of confidence typically focus on model predictions, not label quality. Confident learning (CL) is an alternative approach which focuses instead on label quality by characterizing and…

Machine Learning · Statistics 2022-08-23 Curtis G. Northcutt , Lu Jiang , Isaac L. Chuang