Weakly supervised classification in high energy physics
From MaRDI portal
Abstract: As machine learning algorithms become increasingly sophisticated to exploit subtle features of the data, they often become more dependent on simulations. This paper presents a new approach called weakly supervised classification in which class proportions are the only input into the machine learning algorithm. Using one of the most challenging binary classification tasks in high energy physics - quark versus gluon tagging - we show that weakly supervised classification can match the performance of fully supervised algorithms. Furthermore, by design, the new algorithm is insensitive to any mis-modeling of discriminating features in the data by the simulation. Weakly supervised classification is a general procedure that can be applied to a wide variety of learning problems to boost performance and robustness when detailed simulations are not reliable or not available.
Recommendations
- AN EMPIRICAL STUDY OF BOOSTED NEURAL NETWORK FOR PARTICLE CLASSIFICATION IN HIGH ENERGY COLLISIONS
- Supervised Deep Learning in High Energy Phenomenology: a Mini Review*
- Weakly supervised clustering: learning fine-grained signals from coarse labels
- Nonparametric semi-supervised classification with application to signal detection in high energy physics
- Automated feature selection procedure for particle jet classification
Cites work
- A brief introduction to PYTHIA 8.1
- A general framework for implementing NLO calculations in shower Monte Carlo programs: the POWHEG BOX
- Deep learning in color: towards automated quark/gluon jet discrimination
- FastJet user manual (for version 3.0.2)
- scientific article; zbMATH DE number 2161250 (Why is no real title available?)
- Multiple instance classification: review, taxonomy and comparative study
- PYTHIA 6.4 physics and manual
- Solving the multiple instance problem with axis-parallel rectangles.
- The anti-\(k_t\) jet clustering algorithm
- The automated computation of tree-level and next-to-leading order differential cross sections, and their matching to parton shower simulations
Cited in
(12)- Deep learning in color: towards automated quark/gluon jet discrimination
- Parametrized classifiers for optimal EFT sensitivity
- Nonparametric semi-supervised classification with application to signal detection in high energy physics
- INFERNO: inference-aware neural optimisation
- Automated feature selection procedure for particle jet classification
- Supervised Deep Learning in High Energy Phenomenology: a Mini Review*
- AN EMPIRICAL STUDY OF BOOSTED NEURAL NETWORK FOR PARTICLE CLASSIFICATION IN HIGH ENERGY COLLISIONS
- On asymptotic charges in 3D gravity
- Learning to inflate. A gradient ascent approach to random inflation
- Random forest based multiclass classification approach for highly skewed particle data
- Hardness of learning Boolean functions from label proportions
- Hardness of learning Boolean functions from label proportions
This page was built for publication: Weakly supervised classification in high energy physics
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q683055)
