Message from Imperial Data Science Institute
DataLearning is an interdisciplinary working group of researchers and students developing new technologies based on Data Assimilation and Machine Learning. DataLearning came out of the idea to couple and integrate Data Assimilation with Machine Learning technologies in order to exploit the best features of both.
Next Tuesday 8th March at 16:00 (UK), DataLearning are hosting Savannah Thais from Princeton University.
Title
Graph Neural Networks for Charged Particle Reconstruction at the Large Hadron Collider
Abstract:
The Large Hadron Collider (LHC) collides millions of protons per second, yielding a rich, multi-dimensional dataset with unique mathematical constraints. The raw data from particle detector electronics readouts must be processed to identify the interactions, trajectories, and decays of individual particles in order to enable downstream physics measurements. Traditional approaches to these tasks have relied on constructing physics-motivated variables from the raw data and using these variables as input to physics-based fits and multivariate algorithms. Recently, however, recent work has demonstrated that geometric deep learning approaches can effectively leverage the inherent geometries and relationships in raw collider data, often resulting in more efficient and more accurate particle reconstruction. This talk will describe the use of a range of recent GNN architectures for physics reconstruction tasks and, in particular, will focus on the use of Interaction Networks and instance segmentation methods for charged particle trajectory reconstruction; I will also discuss studies placing equivariant and semi-equivariant constraints on these models and efforts to accelerate model inference for low-latency applications.
Bio:
Savannah Thais is an Associate Research Scholar at Princeton University where she focuses on machine learning (ML). Her current work is centered on using geometric deep learning to build faster, more efficient data reconstruction algorithms for the High-Luminosity Large Hadron Collider and on incorporating physics constraints and expected symmetries into ML architectures. She also works in the AI Ethics space, focusing on regulation of emerging technology, informed consent for data collection and algorithm design/deployment, and community education. She is the founder and Research Director of Community Insight and Impact, an non-profit organization focused on data-driven community needs assessments for vulnerable populations and effective resource allocation. She is extremely passionate about the impacts of science and technology on society and is a strong advocate for improving access to scientific education and literacy, community centered technology development, and equitable data practices. She sits on the Executive Board of Women in Machine Learning, the Executive Committee of the APS Forum on Physics and Society, is a Founding Editor of the Springer AI Ethics journal, and serves as the ML Knowledge Convener for the CMS experiment. She received her PhD in Physics from Yale University in 2019.