Exact computation of maximum rank correlation estimator

In this paper we provide a computation algorithm to get global solution for the maximum rank correlation estimator using mixed integer programming (MIP) approach. We construct new constrained optimization problem by transforming all indicator functions into binary parameters be estimated and show that it is equivalent original problem. also consider an application of best subset prediction can reformulated as MIP. derive non-asymptotic bound tail probability predictive performance measure. investigate MIP empirical example Monte Carlo simulations.