English
Related papers

Related papers: Bounds for the VC Dimension of 1NN Prototype Sets

200 papers

In response to a 1997 problem of M. Vidyasagar, we state a necessary and sufficient condition for distribution-free PAC learnability of a concept class $\mathscr C$ under the family of all non-atomic (diffuse) measures on the domain…

Machine Learning · Computer Science 2010-11-08 Vladimir Pestov

Research on the generalization ability of deep neural networks (DNNs) has recently attracted a great deal of attention. However, due to their complex architectures and large numbers of parameters, measuring the generalization ability of…

Machine Learning · Computer Science 2022-03-18 Runqi Wang , Linlin Yang , Baochang Zhang , Wentao Zhu , David Doermann , Guodong Guo

We study the Vapnik-Chervonenkis (VC) dimension of the set of quadratic residues (i.e. squares) in finite fields, $\mathbb F_q$, when considered as a subset of the additive group. We conjecture that as $q \to \infty$, the squares have the…

Combinatorics · Mathematics 2024-08-02 Brian McDonald , Anurag Sahay , Emmett L. Wyman

This paper focuses on understanding how the generalization error scales with the amount of the training data for deep neural networks (DNNs). Existing techniques in statistical learning require computation of capacity measures, such as VC…

Machine Learning · Computer Science 2021-05-06 Devansh Bisla , Apoorva Nandini Saridena , Anna Choromanska

We consider the problem of determining which classes of functions can be tested more efficiently than they can be learned, in the distribution-free sample-based model that corresponds to the standard PAC learning setting. Our main result…

Machine Learning · Computer Science 2020-12-08 Eric Blais , Renato Ferreira Pinto , Nathaniel Harms

The Sauer-Shelah-Perles Lemma is a cornerstone of combinatorics and learning theory, bounding the size of a binary hypothesis class in terms of its Vapnik-Chervonenkis (VC) dimension. For classes of functions over a $k$-ary alphabet, namely…

Machine Learning · Computer Science 2026-04-15 Steve Hanneke , Qinglin Meng , Shay Moran , Amirreza Shaeiri

Deep learning methods minimise the empirical risk using loss functions such as the cross entropy loss. When minimising the empirical risk, the generalisation of the learnt function still depends on the performance on the training data, the…

Machine Learning · Computer Science 2022-01-19 Antonio Jimeno Yepes

We investigate the feasibility of sample average approximation (SAA) for general stochastic optimization problems, including two-stage stochastic programming without the relatively complete recourse assumption. Instead of analyzing problems…

Optimization and Control · Mathematics 2022-02-22 Henry Lam , Fengpei Li

We study the generalization capacity of group convolutional neural networks. We identify precise estimates for the VC dimensions of simple sets of group convolutional neural networks. In particular, we find that for infinite groups and…

Machine Learning · Computer Science 2022-12-20 Philipp Christian Petersen , Anna Sepliarskaia

We investigate the use of Deep Neural Networks for the classification of image datasets where texture features are important for generating class-conditional discriminative representations. To this end, we first derive the size of the…

Computer Vision and Pattern Recognition · Computer Science 2016-06-22 Saikat Basu , Manohar Karki , Robert DiBiano , Supratik Mukhopadhyay , Sangram Ganguly , Ramakrishna Nemani , Shreekant Gayaka

The VC dimension of the Ising perceptron with binary patterns is calculated by numerical enumerations for system sizes N <= 31. It is significantly larger than N/2. The data suggest that there is probably no well defined asymptotic…

Condensed Matter · Physics 2009-10-28 S. Mertens

We provide a negative resolution to a conjecture of Steinke and Zakynthinou (2020a), by showing that their bound on the conditional mutual information (CMI) of proper learners of Vapnik--Chervonenkis (VC) classes cannot be improved from $d…

Machine Learning · Computer Science 2020-11-06 Mahdi Haghifam , Gintare Karolina Dziugaite , Shay Moran , Daniel M. Roy

The capacity of a learning machine is measured by its Vapnik-Chervonenkis dimension, and learning machines with a low VC dimension generalize better. It is well known that the VC dimension of SVMs can be very large or unbounded, even though…

Machine Learning · Computer Science 2017-05-02 Jayadeva , Suresh Chandra , Siddarth Sabharwal , Sanjit S. Batra

In classical statistical learning theory, one of the most well studied problems is that of binary classification. The information-theoretic sample complexity of this task is tightly characterized by the Vapnik-Chervonenkis (VC) dimension. A…

Quantum Physics · Physics 2021-05-10 Matthias C. Caro

The VC-dimension of a family of sets is a measure of its combinatorial complexity used in machine learning theory, computational geometry, and even model theory. Computing the VC-dimension of the $k$-fold union of geometric set systems has…

Combinatorics · Mathematics 2025-01-20 Pantelis E. Eleftheriou , Aris Papadopoulos , Francis Westhead

In response to a 1997 problem of M. Vidyasagar, we state a criterion for PAC learnability of a concept class $\mathscr C$ under the family of all non-atomic (diffuse) measures on the domain $\Omega$. The uniform Glivenko--Cantelli property…

Machine Learning · Statistics 2013-03-27 Vladimir Pestov

Since its introduction by Vapnik and Chervonenkis in the 1960s, the VC dimension and its variants have played a central role in numerous fields. In this paper, we investigate several variants of the VC dimension and their applications to…

Combinatorics · Mathematics 2025-04-04 Guorong Gao , Jie Ma , Mingyuan Rong , Tuan Tran

We study the Vapnik-Chervonenkis (VC) density of definable families in certain stable first-order theories. In particular we obtain uniform bounds on VC density of definable families in finite U-rank theories without the finite cover…

Logic · Mathematics 2016-02-10 M. Aschenbrenner , A. Dolich , D. Haskell , D. Macpherson , S. Starchenko

The study of strategic or adversarial manipulation of testing data to fool a classifier has attracted much recent attention. Most previous works have focused on two extreme situations where any testing data point either is completely…

Machine Learning · Computer Science 2021-06-14 Ravi Sundaram , Anil Vullikanti , Haifeng Xu , Fan Yao

This paper presents some finite combinatorics of set systems with applications to model theory, particularly the study of dependent theories. There are two main results. First, we give a way of producing lower bounds on VC_ind-density, and…

Logic · Mathematics 2016-02-10 Hunter R. Johnson