English
Related papers

Related papers: Measurability Aspects of the Compactness Theorem f…

200 papers

Machine Learning models should ideally be compact and robust. Compactness provides efficiency and comprehensibility whereas robustness provides resilience. Both topics have been studied in recent years but in isolation. Here we present a…

Machine Learning · Computer Science 2021-03-16 Omri Armstrong , Ran Gilad-Bachrach

Measurability with respect to ideals is tightly connected with absoluteness principles for certain forcing notions. We study a uniformization principle that postulates the existence of a uniformizing function on a large set, relative to a…

Logic · Mathematics 2022-05-31 Sandra Müller , Philipp Schlicht

A measurable map between measure spaces is shown to have bounded compression if and only if its image via the measure-algebra functor is Lipschitz-continuous w.r.t. the measure-algebra distances. This provides a natural interpretation of…

Metric Geometry · Mathematics 2024-03-28 Lorenzo Dello Schiavo

For infinite products of compact spaces, Tychonoff's theorem asserts that their product is compact, in the product topology. Tychonoff's theorem is shown to be equivalent to the axiom of choice. In this paper, we show that any countable…

General Mathematics · Mathematics 2021-11-05 Garimella Sagar , Duggirala Ravi

Recently, a series of works have started studying variations of concepts from learning theory for product spaces, which can be collected under the name high-arity learning theory. In this work, we consider a high-arity variant of sample…

Machine Learning · Computer Science 2026-05-15 Leonardo N. Coregliano , William Opich

We study M-separability as well as some other combinatorial versions of separability. In particular, we show that the set-theoretic hypothesis b=d implies that the class of selectively separable spaces is not closed under finite products,…

General Topology · Mathematics 2010-10-13 Dušan Repovš , Lyubomyr Zdomskyy

List learning is a variant of supervised classification where the learner outputs multiple plausible labels for each instance rather than just one. We investigate classical principles related to generalization within the context of list…

Machine Learning · Computer Science 2026-03-24 Steve Hanneke , Shay Moran , Tom Waknine

The sample compression theory provides generalization guarantees for predictors that can be fully defined using a subset of the training dataset and a (short) message string, generally defined as a binary sequence. Previous works provided…

Machine Learning · Computer Science 2025-03-12 Mathieu Bazinet , Valentina Zantedeschi , Pascal Germain

Every beginning real analysis student learns the classic Heine-Borel theorem, that the interval [0,1] is compact. In this article, we present a proof of this result that doesn't involve the standard techniques such as constructing a…

History and Overview · Mathematics 2008-09-12 Matthew Macauley , Brian Rabern , Landon Rabern

We derive sufficient conditions for sampling with derivatives in shift-invariant spaces generated by a periodic exponential B-spline. The sufficient conditions are expressed with a new notion of measuring the gap between consecutive…

Functional Analysis · Mathematics 2023-11-15 Karlheinz Gröchenig , Irina Shafkulovska

In this paper, we investigate the roles of compact sets in the space of tempered distributions $\mathscr{S}^{\prime}$. The key notion is "k-spaces", which constitute a fairly general class of topological spaces. In a k-space, the system of…

Functional Analysis · Mathematics 2010-09-09 Kei Harada , Hayato Saigo

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

We demonstrate a compactness result holding broadly across supervised learning with a general class of loss functions: Any hypothesis class $H$ is learnable with transductive sample complexity $m$ precisely when all of its finite…

Machine Learning · Computer Science 2024-10-31 Julian Asilis , Siddartha Devic , Shaddin Dughmi , Vatsal Sharan , Shang-Hua Teng

A new line of research uses compression methods to measure the similarity between signals. Two signals are considered similar if one can be compressed significantly when the information of the other is known. The existing compression-based…

Computer Vision and Pattern Recognition · Computer Science 2019-09-30 Tanaya Guha , Rabab K. Ward

The compactness phenomenon is one of the featured aspects of structuralism in mathematics. In simple and broad words, a compactness property holds in a structure if a related property is satisfied by sufficiently many substructures of that…

Logic · Mathematics 2024-08-29 Rahman Mohammadpour

Data compression capability of "Compressed sensing (sampling)" in signal discretization is numerically evaluated and found to be far from the theoretical upper bound defined by signal sparsity. It is shown that, for the cases when ordinary…

Optics · Physics 2015-02-10 L. Yaroslavsky

We investigated the asymptotics of high-rate constrained quantization errors for a compactly supported probability measure P on Euclidean spaces whose quantizers are confined to a closed set S. The key tool is the metric projection of K…

Metric Geometry · Mathematics 2025-05-19 Chenxing Qian

Postselected quantum metrological scheme is especially advantageous when the final measurements are either very noisy or expensive in practical experiments. In this work, we put forward a general theory on the compression channels in…

Quantum Physics · Physics 2024-06-25 Jing Yang

In this work, we investigate the possibility of compressing a quantum system to one of smaller dimension in a way that preserves the measurement statistics of a given set of observables. In this process, we allow for an arbitrary amount of…

Quantum Physics · Physics 2018-06-26 Andreas Bluhm , Lukas Rauber , Michael M. Wolf

Existing guarantees for algorithms sampling from nonlogconcave measures on $\mathbb{R}^d$ are generally inexplicit or unscalable. Even for the class of measures with logdensities that have bounded Hessians and are strongly concave outside a…

Computation · Statistics 2025-05-27 Martin Chak