SciPost Submission Page
ML-Based Top Taggers: Performance, Uncertainty and Impact of Tower & Tracker Data Integration
by Rameswar Sahu, Kirtiman Ghosh
This Submission thread is now published as
Submission summary
| Authors (as registered SciPost users): | Rameswar Sahu |
| Submission information | |
|---|---|
| Preprint Link: | scipost_202403_00033v2 (pdf) |
| Date accepted: | 2024-11-12 |
| Date submitted: | 2024-09-18 09:21 |
| Submitted by: | Sahu, Rameswar |
| Submitted to: | SciPost Physics |
| Ontological classification | |
|---|---|
| Academic field: | Physics |
| Specialties: |
|
| Approach: | Phenomenological |
Abstract
Machine learning algorithms have the capacity to discern intricate features directly from raw data. We demonstrated the performance of top taggers built upon three machine learning architectures: a BDT that uses jet-level variables (high-level features, HLF) as input, while a CNN trained on the jet image, and a GNN trained on the particle cloud representation of a jet utilizing the 4-momentum (low-level features, LLF) of the jet constituents as input. We found significant performance enhancement for all three classes of classifiers when trained on combined data from calorimeter towers and tracker detectors. The high resolution of the tracking data not only improved the classifier performance in the high transverse momentum region, but the information about the distribution and composition of charged and neutral constituents of the fat jets and subjets helped identify the quark/gluon origin of sub-jets and hence enhances top tagging efficiency. The LLF-based classifiers, such as CNN and GNN, exhibit significantly better performance when compared to HLF-based classifiers like BDT, especially in the high transverse momentum region. Nevertheless, the LLF-based classifiers trained on constituents' 4-momentum data exhibit substantial dependency on the jet modeling within Monte Carlo generators. The composite classifiers, formed by stacking a BDT on top of a GNN/CNN, not only enhance the performance of LLF-based classifiers but also mitigate the uncertainties stemming from the showering and hadronization model of the event generator. We have conducted a comprehensive study on the influence of the fat jet's reconstruction and labeling procedure on the efficiency of the classifiers. We have shown the variation of the classifier's performance with the transverse momentum of the fat jet.
Author indications on fulfilling journal expectations
- Provide a novel and synergetic link between different research areas.
- Open a new pathway in an existing or a new research direction, with clear potential for multi-pronged follow-up work
- Detail a groundbreaking theoretical/experimental/computational discovery
- Present a breakthrough on a previously-identified and long-standing research stumbling block
List of changes
1) We have significantly shortened the introduction by removing content that is not directly pertinent to the core focus of our work.
2) We have removed details regarding the LorentzNet model in the model section of our paper and referred the readers to the original paper for details.
3) We have moved the validation section to the appendix.
4) We have merged our findings into a single section, keeping only the relevant information in the main body of our paper.
5) We have significantly shortened the result section by keeping only the relevant results.
Published as SciPost Phys. 17, 166 (2024)
Reports on this Submission
Report
The authors have addressed all of the questions and concerns raised in my previous report, resulting in a substantial improvement in the quality of the manuscript. I am satisfied with the revisions made and recommend this paper for publication.
Recommendation
Publish (meets expectations and criteria for this Journal)
Report #2 by Anonymous (Referee 1) on 2024-11-3 (Invited Report)
- Cite as: Anonymous, Report on arXiv:scipost_202403_00033v2, delivered 2024-11-03, doi: 10.21468/SciPost.Report.10030
Report
The authors have improved the manuscript a lot, particularly the introduction and conclusions. I do think this paper now meets the criteria to be published in SciPost Physics Core. While the paper and the results are valuable, I do not think the techniques studied are new or novel enough to warrant publication in SciPost Physics.
Recommendation
Accept in alternative Journal (see Report)
Report
The paper is much more clearly written now. As requested in my previous report, important definitions are now explicitly stated which make them easier to refer to while reading the paper. The authors have sufficiently addressed the main concerns presented in my previous report and I find the revised version acceptable for publication.
Recommendation
Publish (meets expectations and criteria for this Journal)