An Efficient Monte-Carlo Method to Make a Geometric Graph with a Fixed Connectivity

Abstract

We present a Markov chain Monte-Carlo (MCMC) method to make a geometric graph which satisfies the following two conditions: (i) The degree of each vertex is fixed to a positive integer $k$. (ii) The probability that two vertices located on a $d$-dimensional hypercubic lattice are connected by an edge is proportional to $d_{ij}^{-\alpha }$, where $d_{ij}$ is the distance between the two vertices and $\alpha$ is a positive exponent. We introduce a reverse update method and a list-based update method for the MCMC method. The graph is updated efficiently by the MCMC method since the two update methods work complementarily. We also investigate a ferromagnetic Ising model defined on the geometric graph as a test case. As a result, we have confirmed that the nature of ferromagnetic transition significantly depends on the exponent $\alpha$.

26 pages, 21 figures

References in corpus (6)

• On the scaling of the chemical distance in long-range percolation models
• Study of the de Almeida-Thouless line using power-law diluted one-dimensional Ising spin glasses
• Order-N Cluster Monte Carlo Method for Spin Systems with Long-range Interactions
• Diluted one-dimensional spin glasses with power law decaying interactions
• Monte Carlo studies of the one-dimensional Ising spin glass with power-law interactions
• Kernel method for corrections to scaling

Cited by in corpus (1)

• Construction of a Neural Network with Temperature-Dependent Recall Patterns