English
Related papers

Related papers: Binary perceptrons capacity via fully lifted rando…

200 papers

The neutrinoless double-beta decay process $nn\rightarrow ppee$ within the light Majorana-exchange scenario is studied using the relativistic pionless effective field theory (EFT) in finite-volume cubic boxes with the periodic boundary…

High Energy Physics - Lattice · Physics 2025-09-30 Y. L. Yang , P. W. Zhao

We consider a family of dense $G_{\delta}$ subsets of $[0,1]$, defined as intersections of unions of small uniformly distributed intervals, and study their capacity. Changing the speed at which the lengths of generating intervals decrease,…

Dynamical Systems · Mathematics 2025-11-17 Victor Kleptsyn , Fernando Quintino

In this article, we establish a central limit theorem for the capacity of the range process for a class of $d$-dimensional symmetric $\alpha$-stable random walks with the index satisfying $d > 5\alpha /2$. Our approach is based on…

Probability · Mathematics 2021-04-20 Wojciech Cygan , Nikola Sandrić , Stjepan Šebek

We find a new formula for the limit of the capacity of certain sequences of multidimensional semiconstrained systems as the dimension tends to infinity. We do so by generalizing the notion of independence entropy, originally studied in the…

Dynamical Systems · Mathematics 2017-09-19 Ohad Elishco , Tom Meyerovitch , Moshe Schwartz

We present a systematic study of the family of positive definite (p.d.) kernels with the use of their associated feature maps and feature spaces. For a fixed set $X$, generalizing Loewner, we make precise the corresponding partially ordered…

Functional Analysis · Mathematics 2025-01-22 Palle E. T. Jorgensen , James Tian

Empirical evidence suggests that heavy-tailed degree distributions occurring in many real networks are well-approximated by power laws with exponents $\eta$ that may take values either less than and greater than two. Models based on various…

Machine Learning · Statistics 2018-07-10 Benjamin Bloem-Reddy , Adam Foster , Emile Mathieu , Yee Whye Teh

We construct a class of renormalizable models for lepton mixing that generate predictions given in terms of the charged-lepton mass ratios. We show that one of those models leads, when one takes into account the known experimental values,…

High Energy Physics - Phenomenology · Physics 2018-04-09 D. Jurciukonis , L. Lavoura

Efron's two-group model is widely used in large scale multiple testing. This model assumes that test statistics are mutually independent, however in realistic settings they are typically dependent, and taking the dependence into account can…

Methodology · Statistics 2022-12-20 Rajesh Karmakar , Ruth Heller , Saharon Rosset

We investigate the question of when free structures of infinite rank (in a variety) possess model-theoretic properties like categoricity in higher power, saturation, or universality. Concentrating on left $R$-modules we show, among other…

Rings and Algebras · Mathematics 2025-01-08 Anand Pillay , Philipp Rothmaler

We have experimentally investigated a chaotic reverberation chamber in the regime of strong modal overlap ($1{<}d{<}150$) varying the opening as well as the coupling strength $\kappa$ of the two attached antennas. We find a good agreement…

Disordered Systems and Neural Networks · Physics 2020-10-08 Ulrich Kuhl , Olivier Legrand , Fabrice Mortessagne , Khalid Oubaha , Martin Richter

We derive, from conformal invariance and quantum gravity, the multifractal spectrum f(alpha,c) of the harmonic measure (or electrostatic potential, or diffusion field) near any conformally invariant fractal in two dimensions, corresponding…

Statistical Mechanics · Physics 2016-08-31 Bertrand Duplantier

In this paper, we address the problem of how many randomly labeled patterns can be correctly classified by a single-layer perceptron when the patterns are correlated with each other. In order to solve this problem, two analytical schemes…

Disordered Systems and Neural Networks · Physics 2016-12-15 Takashi Shinzato , Yoshiyuki Kabashima

Random matrix ensembles with Dyson index $\beta=L^{2}$ describe systems of $M$ charge-$L$ particles interacting logarithmically in the presence of an external potential, yet exact formulas for their physical observables have remained…

Mathematical Physics · Physics 2026-01-06 Christopher D. Sinclair

In this paper we give the complete characterization of the boundedness of the generalized fractional maximal operator $$ M_{\phi,\Lambda^{\alpha}(b)}f(x) : = \sup_{Q \ni x} \frac{\|f \chi_Q\|_{\Lambda^{\alpha}(b)}}{\phi (|Q|)} \qquad (x \in…

Functional Analysis · Mathematics 2020-02-05 Rza Mustafayev , Nevin Bilgiçli

We perform accurate numerical experiments with fully-connected (FC) one-hidden layer neural networks trained with a discretized Langevin dynamics on the MNIST and CIFAR10 datasets. Our goal is to empirically determine the regimes of…

Disordered Systems and Neural Networks · Physics 2024-01-23 P. Baglioni , R. Pacelli , R. Aiudi , F. Di Renzo , A. Vezzani , R. Burioni , P. Rotondo

We study properties of strongly coupled CFT's with non-zero background electric charge in 1+1 dimensions by studying the dual gravity theory - which is a charged BTZ black hole. Correlators of operators dual to scalars, gauge fields and…

High Energy Physics - Theory · Physics 2014-11-20 Debaprasad Maity , Swarnendu Sarkar , B. Sathiapalan , R. Shankar , Nilanjan Sircar

The rational Dunkl operators are commuting differential-reflection operators on the Euclidean space $R^d$ associated with a root system, that contain some non-local refection terms, and the associated Hardy space is defined by means of the…

Functional Analysis · Mathematics 2022-12-20 Jiaxi Jiu , Zhongkai Li

We develop a flexible feature selection framework based on deep neural networks that approximately controls the false discovery rate (FDR), a measure of Type-I error. The method applies to architectures whose first layer is fully connected.…

Machine Learning · Statistics 2026-02-10 Kazuma Sawaya

In this work we shall study a class of $f(R,\phi)$ gravity models which during the inflationary era, which is the large curvature regime, result to an effective inflationary Lagrangian that contains a rescaled Einstein-Hilbert term $\alpha…

General Relativity and Quantum Cosmology · Physics 2022-03-14 V. K. Oikonomou , Ifigeneia Giannakoudi , Achilles Gitsis , Konstantinos-Rafail Revis

The input-constrained erasure channel with feedback is considered, where the binary input sequence contains no consecutive ones, i.e., it satisfies the $(1,\infty)$-RLL constraint. We derive the capacity for this setting, which can be…

Information Theory · Computer Science 2015-03-12 Oron Sabag , Haim H. Permuter , Navin Kashyap