Machine Learning for Fundamental Physics: from the Smallest to the Largest Scales

• David Shih

Room: M R070 David Shih is a Professor in the New High Energy Theory Center at Rutgers University. His current research focuses on machine learning and its enormous potential to answer the major open questions of fundamental physics -- such as the nature of dark matter and new particles and forces beyond the Standard Model -- using big datasets from particle colliders and astronomy. His work has touched on many key topics at the intersection of ML and fundamental physics, including generative models, anomaly detection, AI fairness, feature selection, and interpretability. Prior to being an ML physicist, David has also made important contributions to a broad range of experimental and theoretical topics, including experimental neutrino physics, x-ray astronomy, string theory and quantum gravity, and the phenomenology of the Large Hadron Collider. David received a B.A. in Physics and Mathematics at Harvard University, an M.Phil from the Institute of Astronomy at the University of Cambridge, and his Ph.D. from Princeton University.

On unreasonable efficiency of large language models for science

• Artem Maevskiy
• Andrey Ustyuzhanin

Room: M R070

Toward Building Large HEP Models with Self-Supervised Learning

• Michael Kagan

Room: M R070 Michael Kagan is a Lead Staff Scientist at SLAC National Accelerator Laboratory. Michael received his B.S. in Physics and Mathematics at the University of Michigan, where he first worked in High Energy Physics on the CDF experiment. Michael received his Ph.D. from Harvard University, where he worked on the ATLAS experiment at CERN, focusing on some of the earliest measurements on W and Z bosons at the LHC. Michael did his postdoctoral work at SLAC National Laboratory, and subsequently became a Panofsky Fellow at SLAC. Michael’s work focuses on the study of the Higgs Boson and the search for new physics at the ATLAS experiment at the LHC, and on the development of Machine Learning methods for fundamental physics in order to maximize the physics potential of current and future physics experiments.

Fast and furious AI-machines for physics at the LHC

• Andrea Coccaro

Room: M R070 Andrea Coccaro is a research scientist at INFN and a member of the ATLAS and FASER collaborations at the LHC. He obtained his PhD in Physics at the University of Genoa, and then worked as a post-doctoral researcher first at the University of Washington and then at the University of Geneva. His main interests are triggering strategies, jet classification and analyses with heavy-flavoured jets or unconventional signatures in the final state. Lately he focused on the development and application of machine learning methods, in particular in the context of fast inference and classification of hadronic objects.

Optimal Transport for Transfer Learning and Algorithmic Fairness Problems Arising in High-Energy Physics

• Mikael Kuusela

Room: M R070 Dr. Mikael Kuusela is an Assistant Professor of Statistics and Data Science at Carnegie Mellon University. His research focuses on developing statistical methods for analyzing large and complex datasets in the physical sciences. He specializes in questions related to ill-posed inverse problems, spatio-temporal data, uncertainty quantification and statistical learning in climate science, oceanography, remote sensing and particle physics. He works in close collaboration with physical scientists and has various ongoing collaborations with oceanographers working on Argo floats, with NASA scientists working on the OCO-2 mission and with particle physicists at CERN. He obtained his PhD in Statistics in July 2016 from EPFL in Lausanne, Switzerland. He then moved to the US where he was a postdoc at the University of Chicago and at SAMSI before joining Carnegie Mellon in summer 2018. His BSc and MSc degrees are in Engineering Physics and Mathematics from Aalto University.