Weakly supervised classification in high energy physics

Dery, Lucio M.; Nachman, B. P.; Rubbo, F.; Schwartzman, A.

doi:10.1007/jhep05(2017)145

Cited by 105 publications

(97 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Understanding these issues will be a crucial next step. Possibilities are to include uncertainties in the training or to train on data in a weakly supervised or unsupervised fashion [64].…”

Section: Comparisonmentioning

confidence: 99%

The Machine Learning landscape of top taggers

et al. 2019

Self Cite

View full text Add to dashboard Cite

Based on the established task of identifying boosted, hadronically decaying top quarks, we compare a wide range of modern machine learning approaches. Unlike most established methods they rely on low-level input, for instance calorimeter output. While their network architectures are vastly different, their performance is comparatively similar. In general, we find that these new approaches are extremely powerful and great fun.

show abstract

“…Understanding these issues will be a crucial next step. Possibilities are to include uncertainties in the training or to train on data in a weakly supervised or unsupervised fashion [64].…”

Section: Comparisonmentioning

confidence: 99%

The Machine Learning landscape of top taggers

et al. 2019

Self Cite

View full text Add to dashboard Cite

show abstract

“…refs. [33][34][35][36][37][38] and [39][40][41][42][43]. They rely on categorizing and comparing datasets with different expected signal and background admixtures or identifying anomalous events inside large datasets.…”

Section: Introductionmentioning

confidence: 99%

Uncovering latent jet substructure

2019

View full text Add to dashboard Cite

We apply techniques from Bayesian generative statistical modeling to uncover hidden features in jet substructure observables that discriminate between different a priori unknown underlying short distance physical processes in multi-jet events. In particular, we use a mixed membership model known as Latent Dirichlet Allocation to build a data-driven unsupervised top-quark tagger and tt event classifier. We compare our proposal to existing traditional and machine learning approaches to top jet tagging. Finally, employing a toy vector-scalar boson model as a benchmark, we demonstrate the potential for discovering New Physics signatures in multi-jet events in a model independent and unsupervised way.

show abstract

“…Further, studies thus far have used simulation to train the models, which is not reality, and this risks learning the idiosyncrasies of the simulation, and not real physics. Recent ideas for training directly on the data [74][75][76][77] are closely related to the notions of power counting and parametric discrimination power developed here [16,17]. More generally, in order to trust the output of the model and identify the relevant physics that drives the discrimination power, first-principles theoretical calculations that parallel the machine as best as possible are necessary.…”

Section: Discussionmentioning

confidence: 99%

A theory of quark vs. gluon discrimination

Larkoski

Metodiev

2019

J. High Energ. Phys.

View full text Add to dashboard Cite

Understanding jets initiated by quarks and gluons is of fundamental importance in collider physics. Efficient and robust techniques for quark versus gluon jet discrimination have consequences for new physics searches, precision α s studies, parton distribution function extractions, and many other applications. Numerous machine learning analyses have attacked the problem, demonstrating that good performance can be obtained but generally not providing an understanding for what properties of the jets are responsible for that separation power. In this paper, we provide an extensive and detailed analysis of quark versus gluon discrimination from first-principles theoretical calculations. Working in the strongly-ordered soft and collinear limits, we calculate probability distributions for fixed N -body kinematics within jets with up through three resolved emissions (O(α 3 s )). This enables explicit calculation of quantities central to machine learning such as the likelihood ratio, the area under the receiver operating characteristic curve, and reducibility factors within a well-defined approximation scheme. Further, we relate the existence of a consistent power counting procedure for discrimination to ideas for operational flavor definitions, and we use this relationship to construct a power counting for quark versus gluon discrimination as an expansion in e C F −C A 1, the exponential of the fundamental and adjoint Casimirs. Our calculations provide insight into the discrimination performance of particle multiplicity and show how observables sensitive to all emissions in a jet are optimal. We compare our predictions to the performance of individual observables and neural networks with parton shower event generators, validating that our predictions describe the features identified by machine learning.

show abstract

Weakly supervised classification in high energy physics

Cited by 105 publications

References 31 publications

The Machine Learning landscape of top taggers

The Machine Learning landscape of top taggers

Uncovering latent jet substructure

A theory of quark vs. gluon discrimination

Contact Info

Product

Resources

About