Machine Learning for Fundamental Physics: From the Smallest to the Largest Scales
David Shih, Professor, Rutgers University
What new particles and interactions exist beyond the Standard Model? What is the nature of dark matter? What is the origin of the universe? Essential questions of fundamental physics such as these are being confronted with an unprecedented amount of high quality data from the LHC and astronomical surveys. Powerful and cross-cutting machine learning techniques such as generative modeling, density estimation and anomaly detection are increasingly being applied to these datasets, vastly enhancing their discovery potential. In my talk, I will showcase some highlights from this ongoing machine learning revolution that span the range from the smallest scales (LHC data) to the largest scales (astronomical data). I will describe how new techniques developed for model-independent new physics searches and fast simulation at the LHC can also be applied to data from the Gaia space telescope to map out the Milky Way dark matter density, discover new stellar streams, and upsample galaxy simulations.
