English
Related papers

Related papers: Exponentially Consistent Statistical Classificatio…

200 papers

Out-of-distribution generalization capabilities of sequence-to-sequence models can be studied from the lens of two crucial forms of generalization: length generalization -- the ability to generalize to longer sequences than ones seen during…

Machine Learning · Computer Science 2025-05-29 Kartik Ahuja , Amin Mansouri

We initiate a systematic investigation of distribution testing in the framework of algorithmic replicability. Specifically, given independent samples from a collection of probability distributions, the goal is to characterize the sample…

Machine Learning · Computer Science 2025-07-04 Ilias Diakonikolas , Jingyi Gao , Daniel Kane , Sihan Liu , Christopher Ye

Multiple supervised learning scenarios are composed by a sequence of classification tasks. For instance, multi-task learning and continual learning aim to learn a sequence of tasks that is either fixed or grows over time. Existing…

Machine Learning · Statistics 2025-01-10 Verónica Álvarez , Santiago Mazuelas , Jose A. Lozano

Recent work has shown that deep generative models can assign higher likelihood to out-of-distribution data sets than to their training data (Nalisnick et al., 2019; Choi et al., 2019). We posit that this phenomenon is caused by a mismatch…

Machine Learning · Statistics 2019-10-17 Eric Nalisnick , Akihiro Matsukawa , Yee Whye Teh , Balaji Lakshminarayanan

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

We investigate the learning dynamics of classifiers in scenarios where classes are separable or classifiers are over-parameterized. In both cases, Empirical Risk Minimization (ERM) results in zero training error. However, there are many…

Machine Learning · Computer Science 2024-10-23 Julius Martinetz , Christoph Linse , Thomas Martinetz

We study how the training data distribution affects confidence and performance in image classification models. We introduce Embedding Density, a model-agnostic framework that estimates prediction confidence by measuring the distance of test…

Machine Learning · Computer Science 2026-01-28 Maksim Kazanskii , Artem Kasianov

In this paper we propose a computationally efficient multiple hypothesis testing procedure for persistent homology. The computational efficiency of our procedure is based on the observation that one can empirically simulate a null…

Computational Geometry · Computer Science 2022-08-29 Mikael Vejdemo-Johansson , Sayan Mukherjee

Conformal prediction is a general distribution-free approach for constructing prediction sets combined with any machine learning algorithm that achieve valid marginal or conditional coverage in finite samples. Ordinal classification is…

Methodology · Statistics 2024-11-05 Subhrasish Chakraborty , Chhavi Tyagi , Haiyan Qiao , Wenge Guo

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

In many real-world classification problems, the labels of training examples are randomly corrupted. Most previous theoretical work on classification with label noise assumes that the two classes are separable, that the label noise is…

Machine Learning · Statistics 2016-08-08 Gilles Blanchard , Marek Flaska , Gregory Handy , Sara Pozzi , Clayton Scott

As training datasets grow larger, we aspire to develop models that generalize well to any diverse test distribution, even if the latter deviates significantly from the training data. Various approaches like domain adaptation, domain…

Machine Learning · Computer Science 2024-10-10 Andreas Loukas , Karolis Martinkus , Ed Wagstaff , Kyunghyun Cho

A goodness-of-fit test for one-parameter count distributions with finite second moment is proposed. The test statistic is derived from the $L^1$ distance of a function of the probability generating function of the model under the null…

Statistics Theory · Mathematics 2024-06-11 Antonio Di Noia , Lucio Barabesi , Marzia Marcheselli , Caterina Pisani , Luca Pratelli

In the real world, the class of a time series is usually labeled at the final time, but many applications require to classify time series at every time point. e.g. the outcome of a critical patient is only determined at the end, but he…

Machine Learning · Computer Science 2022-08-16 Chenxi Sun , Moxian Song , Derun Can , Baofeng Zhang , Shenda Hong , Hongyan Li

With the widespread success of deep neural networks in science and technology, it is becoming increasingly important to quantify the uncertainty of the predictions produced by deep learning. In this paper, we introduce a new method that…

Machine Learning · Computer Science 2019-08-15 Qingyang Wu , He Li , Lexin Li , Zhou Yu

We propose a general and flexible procedure for testing multiple hypotheses about sequential (or streaming) data that simultaneously controls both the false discovery rate (FDR) and false nondiscovery rate (FNR) under minimal assumptions…

Methodology · Statistics 2019-01-14 Jay Bartroff , Jinlin Song

This paper proposes several tests of restricted specification in nonparametric instrumental regression. Based on series estimators, test statistics are established that allow for tests of the general model against a parametric or…

Econometrics · Economics 2019-09-24 Christoph Breunig

We study a stylized multiple testing problem where the test statistics are independent and assumed to have the same distribution under their respective null hypotheses. We first show that, in the normal means model where the test statistics…

Statistics Theory · Mathematics 2016-04-27 Ery Arias-Castro , Shiyun Chen

Classification is a fundamental problem in machine learning and data mining. During the past decades, numerous classification methods have been presented based on different principles. However, most existing classifiers cast the…

Machine Learning · Computer Science 2019-04-23 Zengyou He , Chaohua Sheng , Yan Liu , Quan Zou

This paper considers a problem of distributed hypothesis testing and social learning. Individual nodes in a network receive noisy local (private) observations whose distribution is parameterized by a discrete parameter (hypotheses). The…

Statistics Theory · Mathematics 2016-05-17 Anusha Lalitha , Tara Javidi , Anand Sarwate
‹ Prev 1 4 5 6 7 8 10 Next ›