English
Related papers

Related papers: Unlabeled Compression Schemes Exceeding the VC-dim…

200 papers

We prove a convergence theorem for U-statistics of degree two, where the data dimension $d$ is allowed to scale with sample size $n$. We find that the limiting distribution of a U-statistic undergoes a phase transition from the…

Statistics Theory · Mathematics 2023-07-04 Kevin H. Huang , Xing Liu , Andrew B. Duncan , Axel Gandy

Compressing giant neural networks has gained much attention for their extensive applications on edge devices such as cellphones. During the compressing process, one of the most important procedures is to retrain the pre-trained models using…

Machine Learning · Computer Science 2019-12-23 Yehui Tang , Shan You , Chang Xu , Boxin Shi , Chao Xu

We study the problem of compression for the purpose of similarity identification, where similarity is measured by the mean square Euclidean distance between vectors. While the asymptotical fundamental limits of the problem - the minimal…

Information Theory · Computer Science 2014-05-13 Fabian Steiner , Steffen Dempfle , Amir Ingber , Tsachy Weissman

Most real-world problems that machine learning algorithms are expected to solve face the situation with 1) unknown data distribution; 2) little domain-specific knowledge; and 3) datasets with limited annotation. We propose Non-Parametric…

Machine Learning · Computer Science 2022-09-20 Zhiying Jiang , Yiqin Dai , Ji Xin , Ming Li , Jimmy Lin

We consider avoidance of permutation patterns with designated gap sizes between pairs of consecutive letters. We call the patterns having such constraints distant patterns (DPs) and we show their relation to other pattern notions…

Combinatorics · Mathematics 2021-05-24 Stoyan Dimitrov

Compressed sensing is the art of reconstructing structured $n$-dimensional vectors from substantially fewer measurements than naively anticipated. A plethora of analytic reconstruction guarantees support this credo. The strongest among them…

Information Theory · Computer Science 2018-12-20 Peter Jung , Richard Kueng , Dustin G. Mixon

We prove several reflection theorems on $D$-spaces, which are Hausdorff topological spaces $X$ in which for every open neighbourhood assignment $U$ there is a closed discrete subspace $D$ such that \[ \bigcup\{U(x): x\in D\}=X. \] The…

Logic · Mathematics 2008-11-10 Mirna Dzamonja

We prove several reflection theorems on $D$-spaces, which are Hausdorff topological spaces $X$ in which for every open neighbourhood assignment $U$ there is a closed discrete subspace $D$ such that \[ \bigcup\{U(x): x\in D\}=X. \] The…

Logic · Mathematics 2007-05-23 Mirna Džamonja

We elaborate on the intimate connection between the largest volume of an empty axis-parallel box in a set of $n$ points from $[0,1]^d$ and cover-free families from the extremal set theory. This connection was discovered in a recent paper of…

Combinatorics · Mathematics 2025-09-09 Matěj Trödler , Jan Volec , Jan Vybíral

We prove a weak version of the $\varepsilon$-Dvoretzky conjecture for normed spaces, showing the existence of a subspace of $\mathbb{R}^n$ of dimension at least $c \log n / |\log \varepsilon|$ in which the given norm is $\varepsilon$-close…

Functional Analysis · Mathematics 2023-07-28 Bo'az Klartag , Tomer Novikov

We establish a tight characterization of the worst-case rates for the excess risk of agnostic learning with sample compression schemes and for uniform convergence for agnostic sample compression schemes. In particular, we find that the…

Machine Learning · Computer Science 2018-05-22 Steve Hanneke , Aryeh Kontorovich

Foundation models are strong data compressors, but when accounting for their parameter size, their compression ratios are inferior to standard compression algorithms. Naively reducing the parameter count does not necessarily help as it…

Machine Learning · Computer Science 2025-05-26 David Heurtel-Depeiges , Anian Ruoss , Joel Veness , Tim Genewein

We study two related quantities which generalize the concept of upper Banach density of a set to two measurable subsets of the plane. The first of them allows us to generalize a classic result on sufficiently large distances realized in a…

Classical Analysis and ODEs · Mathematics 2026-05-05 Bruno Predojević

Above the upper critical dimension, the breakdown of hyperscaling is associated with dangerous irrelevant variables in the renormalization group formalism at least for systems with periodic boundary conditions. While these have been…

Statistical Mechanics · Physics 2014-02-10 Bertrand Berche , Ralph Kenna , Jean-Charles Walter

We consider the problem of providing nonparametric confidence guarantees for undirected graphs under weak assumptions. In particular, we do not assume sparsity, incoherence or Normality. We allow the dimension $D$ to increase with the…

Statistics Theory · Mathematics 2013-09-27 Larry Wasserman , Mladen Kolar , Alessandro Rinaldo

Given natural numbers $k \leq s \leq n$, we ask: what is the minimal VC-dimension of a family $\mathcal{F}$ of $s$-subsets of $[n]$ that covers all $k$-subsets of $[n]$? We first show that for sufficiently large $n$ this number is always…

Combinatorics · Mathematics 2024-01-24 George Peterzil , Johanna Steinmeyer

Let $G = (V,E)$ be an undirected graph with maximum degree $\Delta$ and vertex conductance $\Psi^*(G)$. We show that there exists a symmetric, stochastic matrix $P$, with off-diagonal entries supported on $E$, whose spectral gap…

Probability · Mathematics 2022-03-24 Vishesh Jain , Huy Tuan Pham , Thuy-Duong Vuong

A family S of convex sets in the plane defines a hypergraph H = (S, E) as follows. Every subfamily S' of S defines a hyperedge of H if and only if there exists a halfspace h that fully contains S' , and no other set of S is fully contained…

Computational Geometry · Computer Science 2023-06-22 Nicolas Grelier , Saeed Gh. Ilchi , Tillmann Miltzow , Shakhar Smorodinsky

We present a method to improve the calibration of deep ensembles in the small training data regime in the presence of unlabeled data. Our approach is extremely simple to implement: given an unlabeled set, for each unlabeled data point, we…

Machine Learning · Computer Science 2023-10-05 Konstantinos Pitas , Julyan Arbel

For any positive integers $n\ge d+1\ge 3$, what is the maximum size of a $(d+1)$-uniform set system in $[n]$ with VC-dimension at most $d$? In 1984, Frankl and Pach initiated the study of this fundamental problem and provided an upper bound…

Combinatorics · Mathematics 2025-06-06 Gennian Ge , Zixiang Xu , Chi Hoi Yip , Shengtong Zhang , Xiaochen Zhao