English
Related papers

Related papers: Complexity of random smooth functions on the high-…

200 papers

In this paper, we analyze several methods for approximating gradients of noisy functions using only function values. These methods include finite differences, linear interpolation, Gaussian smoothing and smoothing on a sphere. The methods…

Optimization and Control · Mathematics 2021-03-29 Albert S. Berahas , Liyuan Cao , Krzysztof Choromanski , Katya Scheinberg

Deep neural networks are workhorse models in machine learning with multiple layers of non-linear functions composed in series. Their loss function is highly non-convex, yet empirically even gradient descent minimisation is sufficient to…

Disordered Systems and Neural Networks · Physics 2020-03-18 Simon Becker , Yao Zhang , Alpha A. Lee

We use the Kac-Rice formula and results from random matrix theory to obtain the average number of critical points of a family of high-dimensional empirical loss functions, where the data are correlated $d$-dimensional Gaussian vectors,…

Machine Learning · Computer Science 2026-01-14 Theodoros G. Tsironis , Aris L. Moustakas

We consider the critical properties of points of continuous glass transition as one can find in liquids in presence of constraints or in liquids in porous media. Through a one loop analysis we show that the critical Replica Field Theory…

Statistical Mechanics · Physics 2015-03-20 Silvio Franz , Giorgio Parisi , Federico Ricci-Tersenghi

In large dimension, we study the asymptotic behavior of the mean number of critical points with index k below a level u for an isotropic centered Gaussian random field defined on a family of subsets of $R^d$ depending on d. We prove the…

Probability · Mathematics 2026-02-10 Jean-Marc Azaïs , Céline Delmas

The coordinates along any fixed direction(s), of points on the sphere $S^{n-1}(\sqrt{n})$, roughly follow a standard Gaussian distribution as $n$ approaches infinity. We revisit this classical result from a nonstandard analysis perspective,…

Probability · Mathematics 2024-10-17 Irfan Alam

Using the replica method we calculate the mean spectral density of the Hessian matrix at the global minimum of a random $N \gg 1$ dimensional isotropic, translationally invariant Gaussian random landscape confined by a parabolic potential…

Disordered Systems and Neural Networks · Physics 2019-03-19 Yan V Fyodorov , Pierre Le Doussal

We consider the Cauchy problem with smooth data for compressible Euler equations in many dimensions and concentrate on two cases: solutions with finite mass and energy and solutions corresponding to a compact perturbation of a nontrivial…

Analysis of PDEs · Mathematics 2020-10-30 Olga Rozanova

We define and discuss the notion of pseudospherical surfaces in asymptotic coordinates on time scales. Thus we extend well known notions of discrete pseudospherical surfaces and smooth pseudosperical surfaces on more exotic domains (e.g,…

Differential Geometry · Mathematics 2009-11-20 Jan L. Cieslinski

The classical result of concentration of the Gaussian measure on the sphere in the limit of large dimension induces a natural duality between Gaussian and spherical models of spin glass. We analyse the Legendre variational structure linking…

Disordered Systems and Neural Networks · Physics 2015-06-22 Giuseppe Genovese , Daniele Tantari

We study the 3-spin spherical model with mean-field interactions and Gaussian random couplings. For moderate system sizes of up to 20 spins, we obtain all stationary points of the energy landscape by means of the numerical polynomial…

Statistical Mechanics · Physics 2015-03-20 Dhagash Mehta , Daniel A. Stariolo , Michael Kastner

We present a computational scheme that derives a global polynomial level set parametrisation for smooth closed surfaces from a regular surface-point set and prove its uniqueness. This enables us to approximate a broad class of smooth…

Isotropic Gaussian random fields on the sphere are characterized by Karhunen-Lo\`{e}ve expansions with respect to the spherical harmonic functions and the angular power spectrum. The smoothness of the covariance is connected to the decay of…

Probability · Mathematics 2015-10-26 Annika Lang , Christoph Schwab

We consider three models (elliptic, flat and hyperbolic) of Gaussian random analytic functions distinguished by invariance of their zeroes distribution. Asymptotic normality is proven for smooth functionals (linear statistics) of the set of…

Complex Variables · Mathematics 2007-05-23 Mikhail Sodin , Boris Tsirelson

We calculate moments of free energy's finite size correction for the transition point between ferromagnetic and spin glass phases. We find, that those moments scale with the number of spins with different critical indices, characteristic…

Disordered Systems and Neural Networks · Physics 2007-05-23 D. B. Saakian

We use nonstandard analysis to study the problem of expressing a Gaussian integral in terms of the limiting behavior of a sequence of spherical integrals. Peterson and Sengupta proved that if a Gaussian measure $\mu$ has full support on a…

Probability · Mathematics 2024-10-17 Irfan Alam

Large numbers of ground states of two-dimensional Ising spin glasses with periodic boundary conditions in both directions are calculated for sizes up to 40^2. A combination of a genetic algorithm and Cluster-Exact Approximation is used. For…

Disordered Systems and Neural Networks · Physics 2009-10-31 Alexander K. Hartmann

Critical points of a scalar quantitiy are either extremal points or saddle points. The character of the critical points is determined by the sign distribution of the eigenvalues of the Hessian matrix. For a two-dimensional homogeneous and…

Fluid Dynamics · Physics 2009-11-13 H. Vogel , W. Mohring

The main results of this article are asymptotic formulas for the variance of the number of zeros of a Gaussian random polynomial of degree $N$ in an open set $U \subset C$ as the degree $N \to \infty$, and more generally for the zeros of…

Complex Variables · Mathematics 2007-05-23 Bernard Shiffman , Steve Zelditch

We derive an exact expression for the partition function of the su(m) Haldane-Shastry spin chain, which we use to study the density of levels and the distribution of the spacing between consecutive levels. Our computations show that when…

Statistical Mechanics · Physics 2009-11-11 Federico Finkel , Artemio Gonzalez-Lopez
‹ Prev 1 3 4 5 6 7 10 Next ›