English
Related papers

Related papers: Counting Stationary Points of Random Landscapes as…

200 papers

In this paper, we analyze the decision version of the NK landscape model from the perspective of threshold phenomena and phase transitions under two random distributions, the uniform probability model and the fixed ratio model. For the…

Artificial Intelligence · Computer Science 2011-06-24 J. Culberson , Y. Gao

We present a null model for single- and multi-layered complex systems constructed using homogeneous and isotropic random Gaussian maps. By means of a Kac-Rice formalism, we show that the mean number of fixed points can be calculated as the…

Mathematical Physics · Physics 2018-11-14 J. R. Ipsen , P. J. Forrester

We review recent developments on the characterization of random landscapes in high-dimension. We focus in particular on the problem of characterizing the landscape topology and geometry, discussing techniques to count and classify its…

Disordered Systems and Neural Networks · Physics 2023-04-12 Valentina Ros , Yan V. Fyodorov

Tensor models play an increasingly prominent role in many fields, notably in machine learning. In several applications, such as community detection, topic modeling and Gaussian mixture learning, one must estimate a low-rank signal from a…

Machine Learning · Statistics 2022-06-16 José Henrique de Morais Goulart , Romain Couillet , Pierre Comon

We construct a N-dimensional Gaussian landscape with multiscale, translation invariant, logarithmic correlations and investigate the statistical mechanics of a single particle in this environment. In the limit of high dimension N>>1 the…

Disordered Systems and Neural Networks · Physics 2009-11-13 Yan V. Fyodorov , Jean-Philippe Bouchaud

We investigate the energy landscape of two- and three-dimensional XY models with nearest-neighbor interactions by analytically constructing several classes of stationary points of the Hamiltonian. These classes are analyzed, in particular…

Statistical Mechanics · Physics 2013-03-28 Rachele Nerattini , Michael Kastner , Dhagash Mehta , Lapo Casetti

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

In hep-th/0501082, a field theoretic ``toy model'' for the Landscape was proposed. We show that the considerations of that paper carry through to realistic effective Lagrangians, such as those that emerge out of string theory. Extracting…

High Energy Physics - Theory · Physics 2007-05-23 Jacques Distler , Uday Varadarajan

Phenomenologically interesting scalar potentials are highly atypical in generic random landscapes. We develop the mathematical techniques to generate constrained random potentials, i.e. Slepian models, which can globally represent…

High Energy Physics - Theory · Physics 2020-06-24 Jose J. Blanco-Pillado , Kepa Sousa , Mikel A. Urkiola

We study rough high-dimensional landscapes in which an increasingly stronger preference for a given configuration emerges. Such energy landscapes arise in glass physics and inference. In particular we focus on random Gaussian functions, and…

Disordered Systems and Neural Networks · Physics 2019-01-09 Valentina Ros , Gerard Ben Arous , Giulio Biroli , Chiara Cammarota

We conducted a comprehensive numerical investigation of the energy landscape of the Thomson problem for systems up to $N=150$. Our results show the number of distinct configurations grows exponentially with $N$, but significantly faster…

Soft Condensed Matter · Physics 2025-06-11 Paolo Amore , Victor Figueroa , Enrique Diaz , Jorge A. López , Trevor Vincent

Given a Gaussian Markov random field, we consider the problem of selecting a subset of variables to observe which minimizes the total expected squared prediction error of the unobserved variables. We first show that finding an exact…

Machine Learning · Computer Science 2012-09-27 Satyaki Mahalanabis , Daniel Stefankovic

We present some new theoretical and computational results for the stationary points of bulk systems. First we demonstrate how the potential energy surface can be partitioned into catchment basins associated with every stationary point using…

Condensed Matter · Physics 2007-05-23 David J. Wales , Jonathan P. K. Doye

In classical random matrix theory the Gaussian and chiral Gaussian random matrix models with a source are realized as shifted mean Gaussian, and chiral Gaussian, random matrices with real $(\beta = 1)$, complex ($\beta = 2)$ and real…

Probability · Mathematics 2015-06-16 Peter J. Forrester

Marginal optima are minima or maxima of a function with many nearly flat directions. In settings with many competing optima, marginal ones tend to attract algorithms and physical dynamics. Often, the important family of marginal attractors…

Disordered Systems and Neural Networks · Physics 2024-12-03 Jaron Kent-Dobias

We present a quantum algorithm for efficiently sampling transformed Gaussian random fields on $d$-dimensional domains, based on an enhanced version of the classical moving average method. Pointwise transformations enforcing boundedness are…

Quantum Physics · Physics 2025-08-20 Matthias Deiml , Daniel Peterseim

Random fields in nature often have, to a good approximation, Gaussian characteristics. We present the mathematical framework for a new and simple method for investigating the non-Gaussian contributions, based on counting the maxima and…

Statistical Mechanics · Physics 2012-10-26 T. H. Beuman , A. M. Turner , V. Vitelli

Two canonical problems in geostatistics are estimating the parameters in a specified family of stochastic process models and predicting the process at new locations. A number of asymptotic results addressing these problems over a fixed…

Statistics Theory · Mathematics 2012-10-11 Cari Kaufman , Benjamin Shaby

We consider the problem of approximating ground states of one-dimensional quantum systems within the two most common variational ansatzes, namely the mean field ansatz and Matrix Product States. We show that both for mean field and for…

Quantum Physics · Physics 2010-07-20 Norbert Schuch , J. Ignacio Cirac

Large or very large spatial (and spatio-temporal) datasets have become common place in many environmental and climate studies. These data are often collected in non-Euclidean spaces (such as the planet Earth) and they often present…

Statistics Theory · Mathematics 2023-01-09 Mike Pereira , Nicolas Desassis , Denis Allard