Resonance Searches with Machine Learned Likelihood Ratios

Hollingsworth, Jacob; Whiteson, D.

doi:10.48550/arxiv.2002.04699

Cited by 12 publications

(14 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Refs. [13][14][15][16][17][18][19][20][21][22][23]. In our case, the original sample has asymptotic probability distribution…”

Section: A Learning Event Weightsmentioning

confidence: 81%

“…With neural resampling, we take advantage of the fact that neural networks, when paired with a suitable training algorithm, are excellent likelihood ratio estimators. This fact has been exploited in a variety of recent studies in high-energy physics [13][14][15][16][17][18][19][20][21][22][23]. The technique presented here is most closely related to the OmniFold unfolding algorithm [20], which is based on the Dctr technique for full phase space reweighting [18].…”

mentioning

confidence: 99%

See 1 more Smart Citation

A Neural Resampler for Monte Carlo Reweighting with Preserved Uncertainties

Nachman,

Thaler

2020

Preprint

View full text Add to dashboard Cite

event generators are an essential tool for data analysis in collider physics. To include subleading quantum corrections, these generators often need to produce negative weight events, which leads to statistical dilution of the datasets and downstream computational costs for detector simulation. Recently, the authors of Ref.[1] proposed a positive resampler method to rebalance weights within histogram bins to remove negative weight events. Building on this work, we introduce neural resampling: an unbinned approach to Monte Carlo reweighting based on neural networks that scales well to high-dimensional and variable-dimensional phase space. We pay particular attention to preserving the statistical properties of the event sample, such that neural resampling not only maintains the mean value of any observable but also its Monte Carlo uncertainty. To illustrate our neural resampling approach, we present a case study from the Large Hadron Collider of top quark pair production at next-to-leading order matched to a parton shower. Contents

show abstract

“…Refs. [13][14][15][16][17][18][19][20][21][22][23]. In our case, the original sample has asymptotic probability distribution…”

Section: A Learning Event Weightsmentioning

confidence: 81%

mentioning

confidence: 99%

A Neural Resampler for Monte Carlo Reweighting with Preserved Uncertainties

Nachman,

Thaler

2020

Preprint

View full text Add to dashboard Cite

show abstract

“…An alternative machine learning method developed to fit parameters is DCTR [21]. This method is based upon parameterized neural networks [41] and exploits a relationship between the loss function and the likelihood ratio [42][43][44][45][46][47][48][49][50][51][52].…”

Section: Dctr With Particleflowmentioning

confidence: 99%

Parameter Inference from Event Ensembles and the Top-Quark Mass

Flesher,

Fraser,

Hutchison

et al. 2020

Preprint

View full text Add to dashboard Cite

One of the key tasks of any particle collider is measurement. In practice, this is often done by fitting data to a simulation, which depends on many parameters. Sometimes, when the effects of varying different parameters are highly correlated, a large ensemble of data may be needed to resolve parameter-space degeneracies. An important example is measuring the top-quark mass, where other physical and unphysical parameters in the simulation must be marginalized over when fitting the top-quark mass parameter. We compare three different methodologies for top-quark mass measurement: a classical histogram fitting procedure, similar to one commonly used in experiment optionally augmented with soft-drop jet grooming; a machine-learning method called DCTR; and a linear regression approach, either using a least-squares fit or with a dense linearly-activated neural network. Despite the fact that individual events are totally uncorrelated, we find that the linear regression methods work most effectively when we input an ensemble of events sorted by mass, rather than training them on individual events. Although all methods provide robust extraction of the top-quark mass parameter, the linear network does marginally best and is remarkably simple. For the top study, we conclude that the Monte-Carlo-based uncertainty on current extractions of the top-quark mass from LHC data can be reduced significantly (by perhaps a factor of 2) using networks trained on sorted event ensembles. More generally, machine learning from ensembles for parameter estimation has broad potential for collider physics measurements.

show abstract

“…Broad reviews on the topic of machine learning in particle physics have been written [11][12][13][14][15][16][17], which give an overview of the many applications of machine learning tools in the field. There also exist reviews on the applications of neural networks [18][19][20][21][22]. In the case of BDTs, reviews do exist and discuss their utility in particle physics in general terms [23].…”

Section: Introductionmentioning

confidence: 99%

Boosted decision trees in the era of new physics: a smuon analysis case study

Cornell,

Doorsamy,

Fuks

et al. 2021

Preprint

View full text Add to dashboard Cite

Machine learning algorithms are growing increasingly popular in particle physics analyses, where they are used for their ability to solve difficult classification and regression problems. While the tools are very powerful, they may often be under-or mis-utilised. In the following, we investigate the use of gradient boosting techniques as applicable to a generic particle physics problem. We use as an example a Beyond the Standard Model smuon collider analysis which applies to both current and future hadron colliders, and we compare our results to a traditional cut-and-count approach. In particular, we interrogate the use of metrics in imbalanced datasets which are characteristic of high energy physics problems, offering an alternative to the widely used area under the curve (auc) metric through a novel use of the F-score metric. We present an in-depth comparison of feature selection and investigation using a principal component analysis, Shapley values, and feature permutation methods in a way which we hope will be widely applicable to future particle physics analyses. Moreover, we show that a machine learning model can extend the 95 % confidence level exclusions obtained in a traditional cut-and-count analysis, while potentially bypassing the need for complicated feature selections. Finally, we discuss the possibility of constructing a general machine learning model which is applicable to probe a two-dimensional mass plane.

show abstract

Resonance Searches with Machine Learned Likelihood Ratios

Cited by 12 publications

References 0 publications

A Neural Resampler for Monte Carlo Reweighting with Preserved Uncertainties

A Neural Resampler for Monte Carlo Reweighting with Preserved Uncertainties

Parameter Inference from Event Ensembles and the Top-Quark Mass

Boosted decision trees in the era of new physics: a smuon analysis case study

Contact Info

Product

Resources

About