10
3
v1v2v3 (latest)

Dynamic social learning under graph constraints

Abstract

We introduce a model of graph-constrained dynamic choice with reinforcement modeled by positively α\alpha-homogeneous rewards. We show that its empirical process, which can be written as a stochastic approximation recursion with Markov noise, has the same probability law as a certain vertex reinforced random walk. We use this equivalence to show that for α>0\alpha > 0, the asymptotic outcome concentrates around the optimum in a certain limiting sense when `annealed' by letting α\alpha\uparrow\infty slowly.

View on arXiv
Comments on this paper