Measuring QCD Splittings with Invertible Networks

Bieringer, Sebastian; Butter, Anja; Heimel, Theo; Höche, Stefan; Köthe, Ullrich; Plehn, Tilman; Radev, Stefan T.

doi:10.21468/scipostphys.10.6.126

Cited by 34 publications

(21 citation statements)

References 67 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They allow access to the Jacobian and both directions of the mapping, linking density estimation in the physics and latent spaces in a completely controlled manner. We have used the flexible INN setup successfully for precision event generation [93,94], unfolding detector effects [95], and QCD or astro-particle inference [96,97].…”

Section: Innmentioning

confidence: 99%

What's Anomalous in LHC Jets?

Buss¹,

Dillon²,

Finke³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Searches for anomalies are the main motivation for the LHC and define key analysis steps, including triggers. We discuss how LHC anomalies can be defined through probability density estimates, evaluated in a physics space or in an appropriate neural network latent space. We illustrate this for classical k-means clustering, a Dirichlet variational autoencoder, and invertible neural networks. For two especially challenging scenarios of jets from a dark sector we evaluate the strengths and limitations of each method.

show abstract

Section: Innmentioning

confidence: 99%

What's Anomalous in LHC Jets?

Buss¹,

Dillon²,

Finke³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…We delineated different forms of model misspecification and investigated new methods for reliable detection of simulation gaps and inference errors. The proposed methods are openly available 5 and can be seamlessly integrated into the workflow for end-to-end simulation-based Bayesian parameter estimation with invertible neural networks.…”

Section: Experiments 3: Covid-19 Modelingmentioning

confidence: 99%

“…Further, it builds upon our previous work with invertible neural networks (INNs, [1]) and the BayesFlow framework [29] towards a principled simulation-based Bayesian workflow with INNs. Indeed, the demand for a trustworthy workflow in amortized Bayesian inference increases heavily due to the growing number of applications relying on BayesFlow or related frameworks [5,10,15,34]. The main contributions of our paper are:…”

Section: Introductionmentioning

confidence: 99%

Detecting Model Misspecification in Amortized Bayesian Inference with Neural Networks

Marvin¹,

Bürkner²,

Köthe³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Neural density estimators have proven remarkably powerful in performing efficient simulation-based Bayesian inference in various research domains. In particular, the BayesFlow framework uses a two-step approach to enable amortized parameter estimation in settings where the likelihood function is implicitly defined by a simulation program. But how faithful is such inference when simulations are poor representations of reality? In this paper, we conceptualize the types of model misspecification arising in simulation-based inference and systematically investigate the performance of the BayesFlow framework under these misspecifications. We propose an augmented optimization objective which imposes a probabilistic structure on the latent data space and utilize maximum mean discrepancy (MMD) to detect potentially catastrophic misspecifications during inference undermining the validity of the obtained results. We verify our detection criterion on a number of artificial and realistic misspecifications, ranging from toy conjugate models to complex models of decision making and disease outbreak dynamics applied to real data. Further, we show that posterior inference errors increase as a function of the distance between the true data-generating distribution and the typical set of simulations in the latent summary space. Thus, we demonstrate the dual utility of MMD as a method for detecting model misspecification and as a proxy for verifying the faithfulness of amortized Bayesian inference.

show abstract

“…As before, the challenge of generating many particles covering several orders of magnitude in energy is taken care of by the usual Monte Carlo method. A modified and shower- specific form of the splitting kernels can be extracted from a combination of QCD predictions and data using ML-based inference [45]. While this approach has practical advantages, it is limited by the applicability of the simple splittings picture.…”

Section: Parton Showermentioning

confidence: 99%

Machine Learning and LHC Event Generation

Butter¹,

Plehn²,

Schumann³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

First-principle simulations are at the heart of the high-energy physics research program. They link the vast data output of multi-purpose detectors with fundamental theory predictions and interpretation. This review illustrates a wide range of applications of modern machine learning to event generation and simulation-based inference, including conceptional developments driven by the specific requirements of particle physics. New ideas and tools developed at the interface of particle physics and machine learning will improve the speed and precision of forward simulations, handle the complexity of collision data, and enhance inference as an inverse simulation problem.

show abstract

Measuring QCD Splittings with Invertible Networks

Cited by 34 publications

References 67 publications

What's Anomalous in LHC Jets?

What's Anomalous in LHC Jets?

Detecting Model Misspecification in Amortized Bayesian Inference with Neural Networks

Machine Learning and LHC Event Generation

Contact Info

Product

Resources

About