English
Related papers

Related papers: On sampling symmetric Gibbs distributions on spars…

200 papers

Specify a randomized algorithm that, given a very large graph or network, extracts a random subgraph. What can we learn about the input graph from a single subsample? We derive laws of large numbers for the sampler output, by relating…

Statistics Theory · Mathematics 2017-10-13 Peter Orbanz

In some applied scenarios, the availability of complete data is restricted, often due to privacy concerns; only aggregated, robust and inefficient statistics derived from the data are made accessible. These robust statistics are not…

Methodology · Statistics 2024-02-23 Antoine Luciano , Christian P. Robert , Robin J. Ryder

We consider local Markov chain Monte-Carlo algorithms for sampling from the weighted distribution of independent sets with activity $\l$, where the weight of an independent set $I$ is $\l^{|I|}$. A recent result has established that Gibbs…

Probability · Mathematics 2007-05-23 Elchanan Mossel , Dror Weitz , Nicholas Wormald

Dependency networks (Heckerman et al., 2000) provide a flexible framework for modeling complex systems with many variables by combining independently learned local conditional distributions through pseudo-Gibbs sampling. Despite their…

Machine Learning · Computer Science 2026-04-02 Kazuya Takabatake , Shotaro Akaho

We argue that complex systems must possess long range correlations and illustrate this idea on the example of the mean field spin glass model. Defined on the complete graph, this model has no genuine concept of distance, but the long range…

Disordered Systems and Neural Networks · Physics 2011-02-23 Alain Billoire , Imre Kondor , Jovanka Lukic , Enzo Marinari

We show that in random $K$-uniform hypergraphs of constant average degree, for even $K \geq 4$, local algorithms defined as factors of i.i.d. can not find nearly maximal cuts, when the average degree is sufficiently large. These algorithms…

Probability · Mathematics 2019-11-05 Wei-Kuo Chen , David Gamarnik , Dmitry Panchenko , Mustazee Rahman

Mean-field spin glasses are families of random energy functions (Hamiltonians) on high-dimensional product spaces. In this paper we consider the case of Ising mixed $p$-spin models, namely Hamiltonians $H_N:\Sigma_N\to {\mathbb R}$ on the…

Probability · Mathematics 2020-01-06 Ahmed El Alaoui , Andrea Montanari , Mark Sellke

It is widely expected that systems which fully thermalize are chaotic in the sense of exhibiting random-matrix statistics of their energy level spacings, whereas integrable systems exhibit Poissonian statistics. In this paper, we…

Statistical Mechanics · Physics 2022-09-21 Michael Winer , Richard Barney , Christopher L. Baldwin , Victor Galitski , Brian Swingle

Stratified sampling is a fast and simple method to generate point sets with uniform distribution in hypercubes. However, for the most common paraxial stratfication it has the prominent drawback that the number of sampled points in n…

Computation · Statistics 2018-06-14 Simon Wessing

Most computational models of dependency syntax consist of distributions over spanning trees. However, the majority of dependency treebanks require that every valid dependency tree has a single edge coming out of the ROOT node, a constraint…

Computation and Language · Computer Science 2022-11-29 Miloš Stanojević

We provide a computational method for quickly determining the correct distribution of optically active nanoparticles for a desired response. This is achieved by simulating the optical response of single nanoparticles and performing a…

Optics · Physics 2019-01-03 Phillip Manley , Min Song , Sven Burger , Martina Schmid

Spin glasses are quintessential examples of complex matter. Although much about their order remains uncertain, abstract models of them inform, e.g., the classification of combinatorial optimization problems, the magnetic ordering in metals…

Approximate message passing algorithm enjoyed considerable attention in the last decade. In this paper we introduce a variant of the AMP algorithm that takes into account glassy nature of the system under consideration. We coin this…

Disordered Systems and Neural Networks · Physics 2019-02-07 Fabrizio Antenucci , Florent Krzakala , Pierfrancesco Urbani , Lenka Zdeborová

Spherical spin glasses are canonical models for smooth random functions in high dimensions. In this review, we survey several interrelated lines of research on their geometric structure. We begin with results concerning critical points and…

Probability · Mathematics 2026-01-23 Eliran Subag

We consider the problem of inference in discrete probabilistic models, that is, distributions over subsets of a finite ground set. These encompass a range of well-known models in machine learning, such as determinantal point processes and…

Machine Learning · Computer Science 2018-07-10 Alkis Gotovos , Hamed Hassani , Andreas Krause , Stefanie Jegelka

Random geometric graphs (RGGs) are commonly used to model networked systems that depend on the underlying spatial embedding. We concern ourselves with the probability distribution of an RGG, which is crucial for studying its random…

Information Theory · Computer Science 2018-01-16 Mihai-Alin Badiu , Justin P. Coon

A $k$-modal probability distribution over the discrete domain $\{1,...,n\}$ is one whose histogram has at most $k$ "peaks" and "valleys." Such distributions are natural generalizations of monotone ($k=0$) and unimodal ($k=1$) probability…

Data Structures and Algorithms · Computer Science 2014-09-16 Constantinos Daskalakis , Ilias Diakonikolas , Rocco A. Servedio

We propose a notion of contraction function for a family of graphs and establish its connection to the strong spatial mixing for spin systems. More specifically, we show that for anti-ferromagnetic Potts model on families of graphs…

Data Structures and Algorithms · Computer Science 2015-07-28 Yitong Yin , Chihao Zhang

In this paper we review some recent rigorous results that provide an essentially complete solution of a class of spin glass models introduced by Derrida in the 1980ies. These models are based on Gaussian random processes on $\{-1,1\}^N$…

Disordered Systems and Neural Networks · Physics 2007-05-23 Anton Bovier , Irina Kurkova

This paper addresses the issue of inversion in cases where (1) the observation system is modeled by a linear transformation and additive noise, (2) the problem is ill-posed and regularization is introduced in a Bayesian framework by an a…

Machine Learning · Statistics 2026-02-12 Jean-François Giovannelli