Strongly reinforced Pólya urns with graph-based competition

DOI10.1214/16-AAP1153MaRDI QIDQ341627zbMATH OpenFDO

Authors Remco van der Hofstad, Alexey Kuznetsov, Mark Holmes, Wioletta Ruszel

Publication date 16 November 2016

Published in The Annals of Applied Probability (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1406.0449, https://projecteuclid.org/euclid.aoap/1472745465

zbMATH Keywords

Pólya urnsreinforcement modelstable equilibriastochastic approximation algorithm

Mathematics Subject Classification ID

Interacting random processes; statistical mechanics type models; percolation theory (60K35)

Abstract: We introduce a class of reinforcement models where, at each time step $t$, one first chooses a random subset $A_t$ of colours (independent of the past) from $n$ colours of balls, and then chooses a colour $i$ from this subset with probability proportional to the number of balls of colour $i$ in the urn raised to the power $alpha>1$. We consider stability of equilibria for such models and establish the existence of phase transitions in a number of examples, including when the colours are the edges of a graph, a context which is a toy model for the formation and reinforcement of neural connections.

Recommendations

• Proof of the WARM whisker conjecture for neuronal connections
• Weakly reinforced Pólya urns on countable networks
• A generalized Pólya's urn with graph based interactions: convergence at linearity
• Interacting urns on a finite directed graph
• The Power of Choice in a Generalized Pólya Urn Model

Cited in

(16)

• Weakly reinforced Pólya urns on countable networks
• Finding geodesics on graphs using reinforcement learning
• The trace-reinforced ants process does not find shortest paths
• Vertex reinforced random walks with exponential interaction on complete graphs
• Extremal linkage networks
• Absence of warm percolation in the very strong reinforcement regime
• Nonlinear randomized urn models: a stochastic approximation viewpoint
• Phase transitions in non-linear urns with interacting types
• Proof of the WARM whisker conjecture for neuronal connections
• Interacting urns on a finite directed graph
• Infinite WARM graphs III: strong reinforcement regime
• MATRIX-MFO tandem workshop: Stochastic reinforcement processes and graphs. Abstracts from the MATRIX-MFO tandem workshop held March 5--10, 2023
• Multi-colour competition with reinforcement
• Positive reinforced generalized time-dependent Pólya urns via stochastic approximation
• Planar reinforced k-out percolation
• Pólya urns on hypergraphs

This page was built for publication: Strongly reinforced Pólya urns with graph-based competition

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q341627)