Improving Variational Autoencoders for New Physics Detection at the LHC With Normalizing Flows

Jawahar, Pratik; Aarrestad, Thea Klaeboe; Chernyavskaya, N.; Pierini, M.; Wozniak, K. A.; Ngadiuba, J.; Duarte, J.; Tsan, Steven

doi:10.3389/fdata.2022.803685

Cited by 22 publications

(10 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This problem appears in many areas of science where a weak signal of interest is masked by background events due to light scattering, extraneous emission sources, etc. The location and the width of the signal can sometimes be guessed based on physical considerations; in other cases, consideration of multiple putative signal windows is necessary, as in LHC anomaly detection searches [40][41][42][43][44][45]. In both scenarios, only rough estimates of the position and the width of the signal window are required.…”

Section: Discussionmentioning

confidence: 99%

Model selection and signal extraction using Gaussian Process regression

Gandrakota¹,

Lath²,

Morozov³

et al. 2022

Preprint

View full text Add to dashboard Cite

We present a novel computational approach for extracting weak signals, whose exact location and width may be unknown, from complex background distributions with an arbitrary functional form. We focus on datasets that can be naturally presented as binned integer counts, demonstrating our approach on the CERN open dataset from the ATLAS collaboration at the Large Hadron Collider, which contains the Higgs boson signature. Our approach is based on Gaussian Process (GP) regression -a powerful and flexible machine learning technique that allowed us to model the background without specifying its functional form explicitly, and to separate the background and signal contributions in a robust and reproducible manner. Unlike functional fits, our GP-regression-based approach does not need to be constantly updated as more data becomes available. We discuss how to select the GP kernel type, considering trade-offs between kernel complexity and its ability to capture the features of the background distribution. We show that our GP framework can be used to detect the Higgs boson resonance in the data with more statistical significance than a polynomial fit specifically tailored to the dataset. Finally, we use Markov Chain Monte Carlo (MCMC) sampling to confirm the statistical significance of the extracted Higgs signature.

show abstract

Section: Discussionmentioning

confidence: 99%

Model selection and signal extraction using Gaussian Process regression

Gandrakota¹,

Lath²,

Morozov³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Their objective is the identification of events that can be considered outside the Standard Model (SM) density, and may thus point to new physics beyond the SM (BSM). The use of an explicit SM density estimator has been successful in a variety of anomaly detection tasks [15,[21][22][23][60][61][62][63]. Here, we apply the methods set out in the previous section to the datasets of the Dark Machines Anomaly Score Challenge [38].…”

Section: Anomaly Detectionmentioning

confidence: 99%

“…Of these models, normalizing flows have the particular advantage of simultaneously enabling event generation and likelihood evaluation, the latter of which is useful in other applications. As a result, they have been successfully used for a variety of tasks including event generation [8][9][10][11][12][13][14][15][16][17][18][19][20], anomaly detection [21][22][23], unfolding [24], the calculation of loop integrals [25], and likelihood-free inference [26][27][28].…”

Section: Introductionmentioning

confidence: 99%

Event Generation and Density Estimation with Surjective Normalizing Flows

Verheyen

2022

SciPost Phys.

View full text Add to dashboard Cite

Normalizing flows are a class of generative models that enable exact likelihood evaluation. While these models have already found various applications in particle physics, normalizing flows are not flexible enough to model many of the peripheral features of collision events. Using the framework of [1], we introduce several surjective and stochastic transform layers to a baseline normalizing flow to improve modelling of permutation symmetry, varying dimensionality and discrete features, which are all commonly encountered in particle physics events. We assess their efficacy in the context of the generation of a matrix element-level process, and in the context of anomaly detection in detector-level LHC events.

show abstract

“…The use of normalizing flows as a generative model is has been studied in works such as [105,67] in what is known as flow-based generative models, however such models do not incorporate an autoencoder structure. The use of autoencoder with normalizing flows, replacing optimal transport, is used for the sampling step generative models and this have been studied in [63,95].…”

Section: Generative Model Based On Multisymplectic Integratorsmentioning

confidence: 99%

Multisymplectic Formulation of Deep Learning Using Mean--Field Type Control and Nonlinear Stability of Training Algorithm

Ganaba¹

2022

Preprint

View full text Add to dashboard Cite

As it stands, a robust mathematical framework to analyse and study various topics in deep learning is yet to come to the fore. Nonetheless, viewing deep learning as a dynamical system allows the use of established theories to investigate the behaviour of deep neural networks. In order to study the stability of the training process, in this article, we formulate training of deep neural networks as a hydrodynamics system, which has a multisymplectic structure. For that, the deep neural network is modelled using a stochastic differential equation and, thereby, mean-field type control is used to train it. The necessary conditions for optimality of the mean-field type control reduce to a system of Euler-Poincaré equations, which has the a similar geometric structure to that of compressible fluids. The mean-field type control is solved numerically using a multisymplectic numerical scheme that takes advantage of the underlying geometry. Moreover, the numerical scheme, yields an approximated solution which is also an exact solution of a hydrodynamics system with a multisymplectic structure and it can be analysed using backward error analysis. Further, nonlinear stability yields the condition for selecting the number of hidden layers and the number of nodes per layer, that makes the training stable while approximating the solution of a residual neural network with a number of hidden layers approaching infinity.

show abstract

Improving Variational Autoencoders for New Physics Detection at the LHC With Normalizing Flows

Cited by 22 publications

References 49 publications

Model selection and signal extraction using Gaussian Process regression

Model selection and signal extraction using Gaussian Process regression

Event Generation and Density Estimation with Surjective Normalizing Flows

Multisymplectic Formulation of Deep Learning Using Mean--Field Type Control and Nonlinear Stability of Training Algorithm

Contact Info

Product

Resources

About