Uncertainty-aware machine learning for high energy physics

Machine learning techniques are becoming an integral component of data analysis in high energy physics. These tools provide a significant improvement sensitivity over traditional analyses by exploiting subtle patterns high-dimensional feature spaces. may not be well modeled the simulations used for training machine methods, resulting enhanced to systematic uncertainties. Contrary wisdom constructing strategy that is invariant uncertainties, we study use classifier fully aware uncertainties and their corresponding nuisance parameters. We show this dependence can actually enhance parameters interest. Studies performed using synthetic Gaussian dataset as more realistic physics based on Higgs boson decays tau leptons. For both cases, uncertainty approach achieve better than alternative strategies.