Stein's method

Stein’s method of approximate computation of expectations was introduced by Stanford statistician Charles Stein in the early 1970s. In a nutshell the method advocates to estimate certain classes of expectations in terms of properties of a family of probability-characterising linear operators. Originally developed for purposes of normal approximation, the method and its components were quickly extended to Poisson approximation by Louis Chen and have now been observed to be relevant in an immense variety of problems from probability, statistics, data analysis and beyond. The method’s theoretical foundations have also been shown to lie at the intersection of many fields, including functional analysis, information theory, MCMC, Markov semigroups, Malliavin calculus, PDE theory, optimal transport, …

The literature on this topic is growing at a fast pace and it is hard to keep up. Applications connected with Ivan Nourdin and Giovanni Peccati's Malliavin-Stein method are referenced on a dedicated webpage (maintained by Ivan Nourdin). My purpose is to keep track of "the rest", although to keep things focused I will concentrate on papers which contribute to the Steinian theory (operators, solutions, couplings, ...) outside of the Gaussian and Poisson framework. If you wish to see your article up here, please send me a mail at (yvik.swan at ulb dot be).