List of Tables

Front matter Dedication Epigraph Table of Contents List of Figures List of Tables Acknowledgements Vita Abstract of the Dissertation Introduction I Theoretical Background II Experimental Background III AI/ML and Statistics Background IV Accelerating Simulations with AI V Searches for High Energy Higgs Boson Pairs VI AI for Jets VII Appendix Bibliography

List of Tables

2.1 Dimensions of the fundamental and adjoint representations of the

SO (n)

SU (n)

groups.
2.2 Representations of the Lorentz group and their associated particle fields in the SM.
4.1 Approximate magnitude of the strengths of the four fundamental forces at an energy scale of around 100

MeV

.
4.2 The representations and charges of fermionic and scalar fields in the SM under the

U {(1)}_{Y}

SU {(2)}_{L}

SU {(3)}_{C}

gauge symmetries. The right-handed neutrino is included here for completeness but has not been experimentally confirmed.
6.1 Particles which can reach and be detected by the CMS detector. Lifetimes are given in the rest frame for unstable particles.
8.1 Table of error types, reproduced from Ref. [65].
10.1

W_{1}

distances between real jet mass (

W_{1}^{M}

), averaged particle features (

W_{1}^{P}

), and averaged jet EFPs (

W_{1}^{EFP}

) distributions calculated as a baseline, for three classes of jets.
10.2 Six evaluation scores on different generator and discriminator combinations. Lower is better for all metrics except COV.
10.3 Timing measurements for MPGAN and iGAPT, measured on an NVIDIA 1080 GPU.
11.1 Values, significances, and errors of metrics, as defined in Section 11.2, for each (mixture of) Gaussian distribution(s), for the largest sample size tested.
11.2 Values, significances, and errors of metrics for each jet distribution.
11.3 Evaluation metrics for different jet types and models. The best-performing model on each metric and jet type is highlighted in bold.
13.1 The complete set of input features into GloParT. Three types of inputs are considered: charged PF candidates, neutral PF candidates, and secondary vertices (SVs).
14.1 Offline selection criteria for the signal and fail nonresonant analysis regions.
14.2 Offline selection criteria for analysis regions for the fully-merged Y topology.
14.3 Summary of the effect of different systematic uncertainties on the signal or background yields.
14.4 Signal efficiency scale factors (SFs) and uncertainties for the BDT selection using the Lund jet plane for different nonresonant

H H

signals and analysis regions.
14.5 Signal efficiency scale factors (SFs) and uncertainties using the Lund jet plane for a subset of BSM resonant signals, for our

T_{HVV}

discriminant working point.
16.1 Summary of the relevant symmetries respected by each model tested.
16.2 Median and IQR of relative errors in particle feature reconstruction of selected LGAE and GNNAE models. In each column, the best-performing latent space per model is italicized, and the best model overall is highlighted in bold.
16.3 Median and IQR of relative errors in jet feature reconstruction by selected LGAE and GNNAE models, along with the CNNAE model.
16.4 Anomaly detection metrics by a selected LGAE and GNNAE models, along with the CNNAE model. In each column, the best performing latent space per model is italicized, and the best model overall is highlighted in bold.

Copyright © 2024 Raghav Kansal. All rights reserved.