SciPost Submission Page
A guide for deploying Deep Learning in LHC searches: How to achieve optimality and account for uncertainty
by Benjamin Nachman
This Submission thread is now published as
Submission summary
Authors (as registered SciPost users): | Benjamin Nachman |
Submission information | |
---|---|
Preprint Link: | https://arxiv.org/abs/1909.03081v3 (pdf) |
Date accepted: | 2020-06-10 |
Date submitted: | 2020-03-10 01:00 |
Submitted by: | Nachman, Benjamin |
Submitted to: | SciPost Physics |
Ontological classification | |
---|---|
Academic field: | Physics |
Specialties: |
|
Approach: | Experimental |
Abstract
Deep learning tools can incorporate all of the available information into a search for new particles, thus making the best use of the available data. This paper reviews how to optimally integrate information with deep learning and explicitly describes the corresponding sources of uncertainty. Simple illustrative examples show how these concepts can be applied in practice.
List of changes
I have updated the manuscript in response to the reviewer comments. A detailed response to each reviewer can be found on the reviewer reports page.
Published as SciPost Phys. 8, 090 (2020)
Reports on this Submission
Report #2 by Anonymous (Referee 5) on 2020-5-31 (Invited Report)
- Cite as: Anonymous, Report on arXiv:1909.03081v3, delivered 2020-05-31, doi: 10.21468/SciPost.Report.1725
Report
I reviewed the new version of the paper and I appreciate the effort made by the author to reply to my points raised. A few of them were general remarks (e.g., what was CLs introduced for, what is common practice in HEP within vs beyond the LHC community, now vs the past). While I still disagree on a few of these points (not sure if I made me clear, judging from the answer), I think that these are very minor aspects and I would not slow down the publication process for them.
The message of the paper is correct and it clearly meets the expectations of this journal, so I am happy to recommend its publication.