Litcius/Paper detail

Sharp threshold for the Ising perceptron model

Changji Xu

2021The Annals of Probability14 citationsDOI

Abstract

Consider the discrete cube {−1,1}N and a random collection of half spaces which includes each half space H(x):={y∈{−1,1}N:x·y≥κ N} for x∈{−1,1}N independently with probability p. Is the intersection of these half spaces empty? This is called the Ising perceptron model under Bernoulli disorder. We prove that this event has a sharp threshold, that is, the probability that the intersection is empty increases quickly from ϵ to 1−ϵ when p increases only by a factor of 1+o(1) as N→∞.

Topics & Concepts

MathematicsIsing modelIntersection (aeronautics)CombinatoricsBernoulli's principleEvent (particle physics)Cube (algebra)Discrete mathematicsStatistical physicsPhysicsAerospace engineeringEngineeringQuantum mechanicsThermodynamicsTopological and Geometric Data AnalysisMathematical Dynamics and FractalsMarkov Chains and Monte Carlo Methods
Sharp threshold for the Ising perceptron model | Litcius