ML4Jets2021

Session

Interpretability, Robustness, and Uncertainties

8 Jul 2021, 14:00

Conveners

Interpretability, Robustness, and Uncertainties: Intro

• Daniel Whiteson (University of California Irvine (US))
• Chase Owen Shimmin (Yale University (US))

Interpretability, Robustness, and Uncertainties: Uncertainties

• Daniel Whiteson (University of California Irvine (US))
• Chase Owen Shimmin (Yale University (US))

Interpretability, Robustness, and Uncertainties: Information Content

• Chase Owen Shimmin (Yale University (US))
• Daniel Whiteson (University of California Irvine (US))

Interpretability, Robustness, and Uncertainties: Constructing Observables

• Daniel Whiteson (University of California Irvine (US))
• Chase Owen Shimmin (Yale University (US))

63. Learning Partially Known Stochastic Dynamics with Empirical PAC Bayes

Manuel Haußmann (Universität Heidelberg)

08/07/2021, 14:00

Neural Stochastic Differential Equations model a dynamical environment with neural nets assigned to their drift and diffusion terms. The high expressive power of their nonlinearity comes at the expense of instability in the identification of the large set of free parameters. This worok presents a recipe to improve the prediction accuracy of such models in three steps: i) accounting for...

13. Uncertainties Associated with GAN Generated Datasets

Prasanth Shyamsundar (Fermi National Accelerator Laboratory)

08/07/2021, 14:40

Recently, Generative Adversarial Networks (GANs) trained on samples of traditionally simulated collider events have been proposed as a way of generating larger simulated datasets at a reduced computational cost. In this talk we will present an argument cautioning against the usage of this method to meet the simulation requirements of an experiment, namely that data generated by a GAN cannot...

94. Generative Networks with Uncertainties

Michel Luchmann, Tilman Plehn

08/07/2021, 15:00

We show how Bayesian neural networks can be used to estimate uncertainties associated with regression, classification, and now also generative networks. For generative INNs, the combination of the learned density and uncertainty maps also provide insights into how these networks learn. These results show that criticizing the use of neural networks in LHC physics as black boxes is a...

25. Uncertainty Aware Learning for High Energy Physics

Aishik Ghosh (University of California Irvine (US))

08/07/2021, 15:20

Machine learning techniques are becoming an integral component of data analysis in High Energy Physics (HEP). These tools provide a significant improvement in sensitivity over traditional analyses by exploiting subtle patterns in high-dimensional feature spaces. These subtle patterns may not be well-modeled by the simulations used for training machine learning methods, resulting in an enhanced...

15. Amplifying Statistics with Generative Models

Sebastian Bieringer

08/07/2021, 15:40

Monte Carlo simulations are a vital part of modern particle physics. However classical approaches to these simulations require a vast amount of computational resources. Generative Machine Learning models offer a chance to reduce this strain on computing capabilities by allowing us to generate simulated data at a significantly greater speed. The applicability of such generative models has been...

61. Safety of Quark/Gluon Jet Classification

Alexis Romero

08/07/2021, 16:00

The classification of jets as quark- versus gluon-initiated is an important yet challenging task in the analysis of data from high-energy particle collisions and in the search for physics beyond the Standard Model. The recent integration of deep neural networks operating on low-level detector information has resulted in significant improvements in the classification power of quark/gluon jet...

43. Thoughts on the expressive power and inductive bias of DeepSets and Tree-Based models

Kyle Stuart Cranmer (New York University (US))

08/07/2021, 16:20

Nearly five years ago we introduced tree-based recursive NN models for jet physics, which intuitively reflected the sequence of 1-to-2 splittings found in a parton shower. Subsequently, tree-based models like JUNIPR were developed as (probabilistic) generative models that could be used for classification and reweighing. One result that somewhat undermined the narrative of the connection...

10. Explainable AI for ML Jet Taggers

Christine Angela McLean (SUNY Buffalo)

08/07/2021, 16:40

A framework is presented to extract and understand decision-making information from a deep neural network classifier of jet substructure tagging techniques. The general method studied is to provide expert variables that augment inputs (“eXpert AUGmented” variables, or XAUG variables), then apply layerwise relevance propagation (LRP) to networks that have been provided XAUG variables and those...

100. Bayesian Inference in for Four Tops at the LHC

Ezequiel Alvarez de los Alvarez de San Luis

08/07/2021, 17:00

Four-tops (and its backgrounds) is very hard to model at the LHC, it represents a unique window for detecting top-philic NP, and its current measurements have some tension with theory and predictions. We find that simple, clean and powerful Bayesian Inference can be applied on the data to infer signal and background true distributions. We propose that these results could be used in a novel...

2. Spectral Clustering for Jet Formation

Henry Day-Hall (University of Southampton)

08/07/2021, 17:20

Machine learning (ML) is pushing through boundaries in computational physics.
Jet physics, with it's large and detailed dataset, is particularly well suited.
In this talk I will discuss the application of an unusual ML technique, Spectral Clustering, to jet formation.

Spectral clustering differers from much of ML as it has no "black-box" elements.
Instead, it is based on a simple,...

41. Deep-Learned Event Variables

Doojin Kim (Texas A & M University (US))

08/07/2021, 17:40

The choice of optimal event variables is crucial for achieving the maximal sensitivity of experimental analyses, and suitable kinematic variables for many well-motivated event topologies have been developed in collider physics. Here we propose a deep-learning-based algorithm to design good event variables that are sensitive to a wide range of the unknown model parameter values. We demonstrate...