Dynamic social learning under graph constraints
Optimization and Control
2021-07-27 v3 Machine Learning
Probability
Abstract
We introduce a model of graph-constrained dynamic choice with reinforcement modeled by positively -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 , the asymptotic outcome concentrates around the optimum in a certain limiting sense when `annealed' by letting slowly.
Cite
@article{arxiv.2007.03983,
title = {Dynamic social learning under graph constraints},
author = {Konstantin Avrachenkov and Vivek S. Borkar and Sharayu Moharir and Suhail M. Shah},
journal= {arXiv preprint arXiv:2007.03983},
year = {2021}
}