Adversarial domain adaptation to reduce sample bias of a high energy physics event classifier ^*

Abstract We apply adversarial domain adaptation in unsupervised setting to reduce sample bias a supervised high energy physics events classifier training. make use of neural network containing event and with gradient reversal layer simultaneously enable signal versus background classification on the one hand, while other hand minimizing difference response samples originating from different Monte Carlo models via loss. show successful removal example simulated at Large Hadron Collider t ˉ H $t\bar{t}b\bar{b}$?> b discuss implications limitations method.