Understanding Event-Generation Networks via Uncertainties

Following the growing success of generative neural networks in LHC simulations, the crucial question is how to control the networks and assign uncertainties to their event output. We show how Bayesian normalizing flows or invertible networks capture uncertainties from the training and turn them into an uncertainty on the event weight. Fundamentally, the interplay between density and uncertainty estimates indicates that these networks learn functions in analogy to parameter fits rather than binned event counts.

[1]  F. Bishara,et al.  Machine learning amplitudes for faster event generation , 2019, Physical Review D.

[2]  P. Baldi,et al.  How to GAN Higher Jet Resolution , 2020, SciPost Physics.

[3]  Stefan T. Radev,et al.  BayesFlow: Learning Complex Stochastic Models With Invertible Neural Networks , 2020, IEEE Transactions on Neural Networks and Learning Systems.

[4]  G. Kasieczka,et al.  Decoding Photons: Physics in the Latent Space of a BIB-AE Generative Network , 2021, EPJ Web of Conferences.

[5]  Jack Y. Araz,et al.  Combine and conquer: event reconstruction with Bayesian Ensemble Neural Networks , 2021, Journal of High Energy Physics.

[6]  Rob Verheyen,et al.  Phase space sampling and inference from weighted events with autoregressive flows , 2020, SciPost Physics.

[7]  G. Kasieczka,et al.  Getting High: High Fidelity Simulation of High Granularity Calorimeters with High Speed , 2020, Computing and Software for Big Science.

[8]  Ivan Kobyzev,et al.  Normalizing Flows: An Introduction and Review of Current Methods , 2020, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[9]  Maurizio Pierini,et al.  Adversarially Learned Anomaly Detection on CMS open data: re-discovering the top quark , 2020, The European Physical Journal Plus.

[10]  L. Santi,et al.  Towards a computer vision particle flow , 2020, The European Physical Journal C.

[11]  Michelle P. Kuchera,et al.  Simulation of electron-proton scattering events by a Feature-Augmented and Transformed Generative Adversarial Network (FAT-GAN) , 2020, IJCAI.

[12]  Eric Nalisnick,et al.  Normalizing Flows for Probabilistic Modeling and Inference , 2019, J. Mach. Learn. Res..

[13]  Damian Podareanu,et al.  Event generation and statistical sampling for physics with deep generative models and a density information buffer , 2019, Nature Communications.

[14]  Stefan T. Radev,et al.  Measuring QCD Splittings with Invertible Networks , 2020, SciPost Physics.

[15]  A. Butter,et al.  How to GAN Event Unweighting , 2020, 2012.07873.

[16]  Ian Goodfellow,et al.  Generative adversarial networks , 2020, Commun. ACM.

[17]  Matthew D. Klimek,et al.  Improved neural network Monte Carlo simulation , 2020, 2009.07819.

[18]  Kosei Dohi,et al.  Variational Autoencoders for Jet Simulation , 2020, 2009.04842.

[19]  G. Kasieczka,et al.  GANplifying event samples , 2020, SciPost Physics.

[20]  Ullrich Kothe,et al.  Invertible networks or partons to detector and back again , 2020, 2006.06685.

[21]  K. Cranmer,et al.  Flows for simultaneous manifold learning and density estimation , 2020, NeurIPS.

[22]  G. Kasieczka,et al.  Per-object systematics using deep-learned calibration , 2020, SciPost Physics.

[23]  S. Badger,et al.  Using neural networks for efficient evaluation of high multiplicity scattering amplitudes , 2020, Journal of High Energy Physics.

[24]  H. Schulz,et al.  Event generation with normalizing flows , 2020, Physical Review D.

[25]  S. Schumann,et al.  Exploring phase space with Neural Importance Sampling , 2020, SciPost Physics.

[26]  Christina Gao,et al.  i- flow: High-dimensional integration and sampling with normalizing flows , 2020, Mach. Learn. Sci. Technol..

[27]  B. Nachman,et al.  Anomaly detection with density estimation , 2020, Physical Review D.

[28]  Wei Wei,et al.  Calorimetry with deep learning: particle simulation and reconstruction for collider physics , 2019, The European Physical Journal C.

[29]  G. Kasieczka,et al.  How to GAN away Detector Effects , 2019, SciPost Physics.

[30]  B. Nachman.  A guide for deploying Deep Learning in LHC searches: How to achieve optimality and account for uncertainty , 2019, SciPost Physics.

[31]  Jennifer Thompson,et al.  Deep-learning jets with uncertainties and more , 2019, SciPost Physics.

[32]  A. Butter,et al.  How to GAN event subtraction , 2019, SciPost Physics Core.

[33]  Natalia Gimelshein,et al.  PyTorch: An Imperative Style, High-Performance Deep Learning Library , 2019, NeurIPS.

[34]  Tilman Plehn,et al.  How to GAN LHC events , 2019, SciPost Physics.

[35]  Diederik P. Kingma,et al.  An Introduction to Variational Autoencoders , 2019, Found. Trends Mach. Learn..

[36]  Benjamin Nachman,et al.  Machine learning templates for QCD factorization in the search for physics beyond the standard model , 2019, Journal of High Energy Physics.

[37]  Sana Ketabchi Haghighat,et al.  DijetGAN: a Generative-Adversarial Network approach for the simulation of QCD dijet events at the LHC , 2019, Journal of High Energy Physics.

[38]  Maurizio Pierini,et al.  LHC analysis-specific datasets with Generative Adversarial Networks , 2019, ArXiv.

[39]  Rob Verheyen,et al.  Event Generation and Statistical Sampling with Deep Generative Models , 2019 .

[40]  Enrico Bothmann,et al.  Reweighting a parton shower using a neural network: the final-state case , 2018, Journal of High Energy Physics.

[41]  Ullrich Köthe,et al.  Analyzing Inverse Problems with Invertible Neural Networks , 2018, ICLR.

[42]  Thomas Müller,et al.  Neural Importance Sampling , 2018, ACM Trans. Graph..

[43]  Martin Erdmann,et al.  Precise Simulation of Electromagnetic Calorimeter Showers Using a Wasserstein Generative Adversarial Network , 2018, Computing and Software for Big Science.

[44]  C. Frye,et al.  JUNIPR: a framework for unsupervised machine learning in particle physics , 2018, The European Physical Journal C.

[45]  Matthew D. Klimek,et al.  Neural network-based approach to phase space integration , 2018, SciPost Physics.

[46]  David Rousseau,et al.  Further developments of FORM , 2018, Journal of Physics: Conference Series.

[47]  Gilles Louppe,et al.  Deep generative models for fast shower simulation in ATLAS , 2018 .

[48]  J. Monk,et al.  Deep learning as a parton shower , 2018, Journal of High Energy Physics.

[49]  Prafulla Dhariwal,et al.  Glow: Generative Flow with Invertible 1x1 Convolutions , 2018, NeurIPS.

[50]  Finale Doshi-Velez,et al.  Structured Variational Learning of Bayesian Neural Networks with Horseshoe Priors , 2018, ICML.

[51]  Deepak Kar,et al.  Unfolding with Generative Adversarial Networks , 2018, 1806.00433.

[52]  Francesco Pandolfi,et al.  Fast and Accurate Simulation of Particle Detectors Using Generative Adversarial Networks , 2018, Computing and Software for Big Science.

[53]  Martin Erdmann,et al.  Generating and Refining Particle Detector Simulations Using the Wasserstein Distance in Adversarial Networks , 2018, Computing and Software for Big Science.

[54]  Max Welling,et al.  Learning Sparse Neural Networks through L0 Regularization , 2017, ICLR.

[55]  Tom White,et al.  Generative Adversarial Networks: An Overview , 2017, IEEE Signal Processing Magazine.

[56]  Benjamin Nachman,et al.  Accelerating Science with Generative Adversarial Networks: An Application to 3D Particle Showers in Multilayer Calorimeters. , 2017, Physical review letters.

[57]  Alex Kendall,et al.  What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision? , 2017, NIPS.

[58]  Luke de Oliveira,et al.  Learning Particle Physics by Example: Location-Aware Generative Adversarial Networks for Physics Synthesis , 2017, Computing and Software for Big Science.

[59]  Samy Bengio,et al.  Density estimation using Real NVP , 2016, ICLR.

[60]  Aaron Klein,et al.  Bayesian Optimization with Robust Bayesian Neural Networks , 2016, NIPS.

[61]  David M. Blei,et al.  Variational Inference: A Review for Statisticians , 2016, ArXiv.

[62]  Yarin Gal,et al.  Uncertainty in Deep Learning , 2016 .

[63]  Shakir Mohamed,et al.  Variational Inference with Normalizing Flows , 2015, ICML.

[64]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[65]  Diederik P. Kingma,et al.  Variational Dropout and the Local Reparameterization Trick , 2015, NIPS.

[66]  R. Frederix,et al.  The automated computation of tree-level and next-to-leading order differential cross sections, and their matching to parton shower simulations , 2014, 1405.0301.

[67]  Max Welling,et al.  Auto-Encoding Variational Bayes , 2013, ICLR.

[68]  S. Forte,et al.  Parton distributions with QED corrections , 2013, 1308.0598.

[69]  Y. Meng,et al.  Applying Bayesian neural networks to event reconstruction in reactor neutrino experiments , 2007, 0712.4042.

[70]  Pushpalatha C Bhat,et al.  BAYESIAN NEURAL NETWORKS , 2006 .

[71]  S. Saucedo.  Bayesian Neural Networks for Classification , 2006 .

[72]  David Mackay,et al.  Probable networks and plausible predictions - a review of practical Bayesian methods for supervised neural networks , 1995 .

[73]  Geoffrey E. Hinton,et al.  Bayesian Learning for Neural Networks , 1995 .