Weakly Supervised Classification in High Energy Physics
This approach boosts performance and robustness for learning problems where simulations are unreliable or unavailable, particularly in high energy physics.
The paper tackles the problem of machine learning's dependence on detailed simulations by introducing weakly supervised classification, which uses only class proportions as input, and demonstrates that it matches fully supervised performance on quark vs. gluon tagging in high energy physics.
As machine learning algorithms become increasingly sophisticated to exploit subtle features of the data, they often become more dependent on simulations. This paper presents a new approach called weakly supervised classification in which class proportions are the only input into the machine learning algorithm. Using one of the most challenging binary classification tasks in high energy physics - quark versus gluon tagging - we show that weakly supervised classification can match the performance of fully supervised algorithms. Furthermore, by design, the new algorithm is insensitive to any mis-modeling of discriminating features in the data by the simulation. Weakly supervised classification is a general procedure that can be applied to a wide variety of learning problems to boost performance and robustness when detailed simulations are not reliable or not available.