Kyle Cranmer - Some fun examples from the intersection of machine learning and physics

Lecture recorded at the ML in PL 2020 Virtual Event, 18 December 2020. Kyle Cranmer (NYU) Slides available at https://doi.org/10.6084/m9.figshare.1... Abstract: Machine learning and physics have a long history of interactions. Many machine learning techniques have roots in physics, and machine learning techniques have been applied to problems in physics for years. But this interaction has intensified recently, and the interplay touches on many of the most interesting contemporary topics in deep learning including understanding of generalization, generative models, causality, inductive bias, and inference. I will describe some of the results and exploratory work that is being done in this direction.