Data Analysis in High-Energy Physics as a Differentiable Program
Jan 10, 2023234 pages
Supervisors:
Thesis: Other - ,
- Lund U.
- Published: Jan 10, 2023
Report number:
- CERN-THESIS-2023-003
View in:
Citations per year
0 Citations
Abstract: (CERN)
Machine learning methods are now ubiquitous in physics, but often target objectives that are one or two steps removed from our physics goals. A prominent example of this is the discrimination between signal and background processes, which doesnβt account for the presence of systematic uncertainties β something crucial for the calculation of quantities such as the discovery significance and upper limits.To combat this, this thesis shows that physics analysis workflows can be optimized in an end-to-end fashion, including the treatment of nuisance parameters that model systematic uncertainties, provided that the workflow is differentiable. By leveraging automatic differentiation and surrogates for non-differentiable operations, this work has made this possible for the first time, and demonstrates its use in a proof-of-concept scenario.
This thesis will motivate the use of end-to-end optimization as described above, cover the techniques that make it possible, and show recent developments in a high-energy physics context. Future directions that aim to scale and apply these methods will also be highlighted.
In addition to this, a method to interpolate between the signatures of new physics models is presented, which uses normalizing flows. The thesis then goes on to show the use of the technique in a search for a new scalar boson π produced in association with a Higgs boson from a heavy new scalar π. There are also some contributions that interpolate between the event yields with Gaussian processes, and that show how we can use normalizing flows to construct a likelihood ratio-inspired observable.
- boson: scalar
- new physics: signature
- flow
- Higgs particle
- optimization
- machine learning
References(190)
Figures(0)
- [2011]
- [040]