Research Statement
I study particle physics as a member of the ATLAS group at Argonne National Laboratory. My particular interests involve beyond the Standard Model physics and the properties of the Higgs boson. I develop new ways in which machine learning can be used to further these goals. Anomaly detection allows for searches sensitive to a wide range of new physics signatures and advanced Transformer models identify particles with unprecedented accuracy. I use supercomputers to run these algorithms, taking advantage of their massive computing power and speed to improve them.
Research Areas
Physics
Particle physics as part of the ATLAS experiment at CERN
Data Science
Usage of data to reveal truths of the world around us
Machine Learning
Cutting-edge machine learning applied to complex physics problems
Anomaly Detection
Identify unusual signatures in a new paradigm of BSM search
High-Performance Computing
Scaling ML training on some of the largest supercomputers
Current Projects
Systematic-Aware ML Training
Incorporate theoretical and experimental uncertainties into ML training to reduce impact on model performance
Anomaly Detection Using Unsupervised Learning in Search for New Physics
Employ anomaly detection technique in model-independent search for new particles
Resonant Di-Higgs Search in bbll+MET Final State
Search for Beyond the Standard Model signatures coupling to the Higgs boson