We consider the variable selection problem for two-sample tests, aiming to select the most informative variables to distinguish samples from two groups. To solve this problem, we propose a framework based on the kernel maximum mean discrepancy (MMD). Our approach seeks a group of variables with a pre-specified size that maximizes the variance-regularized MMD statistics. This formulation also corresponds to the minimization of asymptotic type-II error while controlling type-I error, as studied in the literature. We present mixed-integer programming formulations and develop exact and approximation algorithms with performance guarantees for different choices of kernel functions. Furthermore, we provide a statistical testing power analysis of our proposed framework. Experiment results on synthetic and real datasets demonstrate the superior performance of our approach.