Speaker
Zhongtian Dong
(University of Kansas)
Description
Symbolic Regression represents a collection of methods to derive the symbolical expression of a formula given numerical values of the variables and the function values. Recent advances in machine learning have improved the performance of symbolic regression, and have attracted attention to use it to solve physics problems. We attempted to use symbolic regression to derive analytical formulas that are needed at various stages of a typical experimental analysis in collider phenomenology. We will demonstrate using two separate applications, that machine learning can derive the analytical expression given the appropriate training data.
Authors
Konstantin Matchev
(University of Florida (US))
Kyoungchul Kong
Zhongtian Dong
(University of Kansas)
