English
Related papers

Related papers: Bounding Embeddings of VC Classes into Maximum Cla…

200 papers

It is conjectured that the recursive teaching dimension of any finite concept class is upper-bounded by the VC-dimension of this class times a universal constant. In this paper, we confirm this conjecture for two rich families of concept…

Discrete Mathematics · Computer Science 2025-02-14 Hans U. Simon

Approximation and learning of classifiers of large data sets by neural networks in terms of high-dimensional geometry and statistical learning theory are investigated. The influence of the VC dimension of sets of input-output functions of…

Machine Learning · Statistics 2025-11-18 Vera Kurkova , Marcello Sanguineti

We study a model of machine teaching where the teacher mapping is constructed from a size function on both concepts and examples. The main question in machine teaching is the minimum number of examples needed for any concept, the so-called…

Combinatorics · Mathematics 2024-02-12 Brigt Håvardstun , Jan Kratochvíl , Joakim Sunde , Jan Arne Telle

By definition, a rigid graph in $\mathbb{R}^d$ (or on a sphere) has a finite number of embeddings up to rigid motions for a given set of edge length constraints. These embeddings are related to the real solutions of an algebraic system.…

Combinatorics · Mathematics 2021-10-26 Evangelos Bartzos , Ioannis Z. Emiris , Raimundas Vidunas

Many practical prediction algorithms represent inputs in Euclidean space and replace the discrete 0/1 classification loss with a real-valued surrogate loss, effectively reducing classification tasks to stochastic optimization. In this…

Machine Learning · Computer Science 2024-11-19 Bogdan Chornomaz , Shay Moran , Tom Waknine

We will establish that the VC dimension of the class of d-dimensional ellipsoids is (d^2+3d)/2, and that maximum likelihood estimate with N-component d-dimensional Gaussian mixture models induces a geometric class having VC dimension at…

Combinatorics · Mathematics 2011-09-21 Yohji Akama , Kei Irie

Contrastive learning produces coherent semantic feature embeddings by encouraging positive samples to cluster closely while separating negative samples. However, existing contrastive learning methods lack principled guarantees on coverage…

Machine Learning · Computer Science 2026-03-30 Yahya Alkhatib , Wee Peng Tay

Supervised dimensionality reduction has emerged as an important theme in the last decade. Despite the plethora of models and formulations, there is a lack of a simple model which aims to project the set of patterns into a space defined by…

Machine Learning · Statistics 2016-10-28 Anthony O. Smith , Anand Rangarajan

This paper studies the minimal dimension required to embed subset memberships ($m$ elements and ${m\choose k}$ subsets of at most $k$ elements) into vector spaces, denoted as Minimal Embeddable Dimension (MED). The tight bounds of MED are…

Machine Learning · Computer Science 2026-01-30 Zihao Wang , Hang Yin , Lihui Liu , Hanghang Tong , Yangqiu Song , Ginny Wong , Simon See

Approximate solutions to various NP-hard combinatorial optimization problems have been found by learned heuristics using complex learning models. In particular, vertex (node) classification in graphs has been a helpful method towards…

Social and Information Networks · Computer Science 2022-11-01 Ali Baran Taşdemir , Tuna Karacan , Emir Kaan Kırmacı , Lale Özkahya

Deep neural networks have consistently represented the state of the art in most computer vision problems. In these scenarios, larger and more complex models have demonstrated superior performance to smaller architectures, especially when…

Computer Vision and Pattern Recognition · Computer Science 2024-08-16 Alexandre Lopes , Fernando Pereira dos Santos , Diulhio de Oliveira , Mauricio Schiezaro , Helio Pedrini

In this note we disprove a conjecture of Kuzmin and Warmuth claiming that every family whose VC-dimension is at most d admits an unlabeled compression scheme to a sample of size at most d. We also study the unlabeled compression schemes of…

Combinatorics · Mathematics 2021-10-15 Dömötör Pálvölgyi , Gábor Tardos

VC-dimension and VC-density are measures of combinatorial complexity of set systems. VC-dimension was first introduced in the context of statistical learning theory, and is tightly related to the sample complexity in PAC learning.…

Logic · Mathematics 2020-08-03 Bjarki Geir Benediktsson , Dugald Macpherson , Isolde Adler

The proliferation of deep learning-based machine vision applications has given rise to a new type of compression, so called video coding for machine (VCM). VCM differs from traditional video coding in that it is optimized for machine vision…

Computer Vision and Pattern Recognition · Computer Science 2023-08-09 Yeongwoong Kim , Hyewon Jeong , Janghyun Yu , Younhee Kim , Jooyoung Lee , Se Yoon Jeong , Hui Yong Kim

We study the simultaneous embeddability of a pair of partitions of the same underlying set into disjoint blocks. Each element of the set is mapped to a point in the plane and each block of either of the two partitions is mapped to a region…

Computational Geometry · Computer Science 2014-08-27 Jan Christoph Athenstädt , Tanja Hartmann , Martin Nöllenburg

In this paper we describe an approach to construct large extendable collections of vectors in predefined spaces of given dimensions. These collections are useful for neural network latent space configuration and training. For classification…

Algebraic Geometry · Mathematics 2025-12-05 Igor V. Netay

A key characteristic of deep recommendation models is the immense memory requirements of their embedding tables. These embedding tables can often reach hundreds of gigabytes which increases hardware requirements and training cost. A common…

Why does the low dimensionality of representations, typically $d\approx 1000$, not prevent modern embedding-based retrieval models from scaling to billions, or even trillions, of data points? To answer this question, we study maximal-margin…

Machine Learning · Computer Science 2026-05-25 Kiril Bangachev , Guy Bresler , Jonathan Kogan , Yury Polyanskiy

Quite recently a teaching model, called "No-Clash Teaching" or simply "NC-Teaching", had been suggested that is provably optimal in the following strong sense. First, it satisfies Goldman and Matthias' collusion-freeness condition. Second,…

Combinatorics · Mathematics 2022-05-06 Hans U. Simon

Deep metric learning aims to learn an embedding space where the distance between data reflects their class equivalence, even when their classes are unseen during training. However, the limited number of classes available in training…

Computer Vision and Pattern Recognition · Computer Science 2022-01-05 Kyungmoon Lee , Sungyeon Kim , Seunghoon Hong , Suha Kwak