Accelerating HEP Science: Inference and Machine Learning at Extreme Scales
This project brings together ASCR and HEP researchers to develop and apply new methods and algorithms in the area of extreme-scale inference and machine learning. The research program melds high-performance computing and techniques for “big data” analysis to enable new avenues of scientific discovery.
The focus is on developing powerful and widely applicable approaches to attack problems that would otherwise be largely intractable. The work at Argonne will focus on solving statistical inverse problems in cosmology by building a new generation of emulation and Bayesian analysis tools, and the application of machine learning methods to cosmological survey images for classification and analysis tasks and for developing an automated method for determining empirical basis sets for large-dimensional data sets.
The results will be of major benefit to all DOE- supported next-generation surveys and will improve the sensitivity and robustness of the final cosmological constraints in multiple ways.