English
Related papers

Related papers: A packing lemma for VCN${}_k$-dimension and learni…

200 papers

Learning high-dimensional distributions is an important yet challenging problem in machine learning with applications in various domains. In this paper, we introduce new techniques to formulate the problem as solving Fokker-Planck equation…

Machine Learning · Computer Science 2021-05-11 Yufan Zhou , Changyou Chen , Jinhui Xu

The VC-dimension, introduced by Vapnik and Chervonenkis in 1968 in the context of learning theory, has in recent years provided a rich source of problems in combinatorial geometry. Given $E\subseteq \mathbb{F}_q^d$ or $E\subseteq…

Combinatorics · Mathematics 2025-11-24 Moustapha Diallo , Brian McDonald

Minimising upper bounds on the population risk or the generalisation gap has been widely used in structural risk minimisation (SRM) -- this is in particular at the core of PAC-Bayesian learning. Despite its successes and unfailing surge of…

Machine Learning · Statistics 2023-10-30 Paul Viallard , Maxime Haddouche , Umut Şimşekli , Benjamin Guedj

Deep neural networks often contain far more parameters than training examples, yet they still manage to generalize well in practice. Classical complexity measures such as VC-dimension or PAC-Bayes bounds usually become vacuous in this…

Machine Learning · Computer Science 2025-08-26 Aviral Dhingra

We study the efficient learnability of geometric concept classes - specifically, low-degree polynomial threshold functions (PTFs) and intersections of halfspaces - when a fraction of the data is adversarially corrupted. We give the first…

Machine Learning · Computer Science 2017-07-06 Ilias Diakonikolas , Daniel M. Kane , Alistair Stewart

Classification by neural nets and by tree-based methods are powerful tools of machine learning. There exist interesting visualizations of the inner workings of these and other classifiers. Here we pursue a different goal, which is to…

Machine Learning · Statistics 2024-07-08 Jakob Raymaekers , Peter J. Rousseeuw

Vapnik--Chervonenkis' theorem is a seminal result in machine learning. It establishes sufficient conditions for empirical probabilities to converge to theoretical probabilities, uniformly over families of events. It also provides an…

Machine Learning · Computer Science 2026-01-26 A. Iosevich , A. Vagharshakyan , E. Wyman

Learning sentence vectors from an unlabeled corpus has attracted attention because such vectors can represent sentences in a lower dimensional and continuous space. Simple heuristics using pre-trained word vectors are widely applied to…

Machine Learning · Computer Science 2019-02-14 Kento Nozawa , Issei Sato

Recently, Brand, Ganian and Simonov introduced a parameterized refinement of the classical PAC-learning sample complexity framework. A crucial outcome of their investigation is that for a very wide range of learning problems, there is a…

Data Structures and Algorithms · Computer Science 2023-08-23 Robert Ganian , Liana Khazaliya , Kirill Simonov

We study the classical and parameterized complexity of computing the positive non-clashing teaching dimension of a set of concepts, that is, the smallest number of examples per concept required to successfully teach an intelligent learner…

Computational Complexity · Computer Science 2025-03-12 Robert Ganian , Liana Khazaliya , Fionn Mc Inerney , Mathis Rocton

An agnostic PAC learning algorithm finds a predictor that is competitive with the best predictor in a benchmark hypothesis class, where competitiveness is measured with respect to a given loss function. However, its predictions might be…

Machine Learning · Computer Science 2021-05-24 Guy N Rothblum , Gal Yona

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

We develop a new high-dimensional statistical learning model which can take advantage of structured correlation in data even in the presence of randomness. We completely characterize learnability in this model in terms of…

Machine Learning · Statistics 2025-09-26 Leonardo N. Coregliano , Maryanthe Malliaris

This work addressed the problem of learning a network with communication between vertices. The communication between vertices is presented in the form of perturbation on the measure. We studied the scenario where samples are drawn from a…

Machine Learning · Statistics 2021-11-23 Yihan He

The Vapnik-Chervonenkis dimension provides a notion of complexity for systems of sets. If the VC dimension is small, then knowing this can drastically simplify fundamental computational tasks such as classification, range counting, and…

Computational Geometry · Computer Science 2019-11-18 Anne Driemel , André Nusser , Jeff M. Phillips , Ioannis Psarros

Approximate learning machines have become popular in the era of small devices, including quantised, factorised, hashed, or otherwise compressed predictors, and the quest to explain and guarantee good generalisation abilities for such…

Machine Learning · Computer Science 2022-03-16 Andrew J. Turner , Ata Kabán

We show a generic reduction from multiclass differentially private PAC learning to binary private PAC learning. We apply this transformation to a recently proposed binary private PAC learner to obtain a private multiclass learner with…

Machine Learning · Computer Science 2021-07-26 Mark Bun , Marco Gaboardi , Satchit Sivakumar

In this paper, we derive generalization bounds for the two primary classes of graph neural networks (GNNs), namely graph convolutional networks (GCNs) and message passing GNNs (MPGNNs), via a PAC-Bayesian approach. Our result reveals that…

Machine Learning · Computer Science 2020-12-15 Renjie Liao , Raquel Urtasun , Richard Zemel

We use a formal correspondence between thermodynamics and inference, where the number of samples can be thought of as the inverse temperature, to study a quantity called ``learning capacity'' which is a measure of the effective…

Machine Learning · Computer Science 2024-10-22 Daiwei Chen , Wei-Kai Chang , Pratik Chaudhari

We derive the calculation of two critical numbers predicting the behavior of perceptron networks. First, we derive the calculation of what we call the lossless memory (LM) dimension. The LM dimension is a generalization of the…

Neural and Evolutionary Computing · Computer Science 2018-09-11 Gerald Friedland , Mario Krell