DCTRGAN: improving the precision of generative models with reweighting

Significant advances in deep learning have led to more widely used and precise neural network-based generative models such as Generative Adversarial Networks (GANS). We introduce a post-hoc correction to deep generative models to further improve their fidelity, based on the Deep neural networks using the Classification for Tuning and Reweighting (DCTR) protocol. The correction takes the form of a reweighting function that can be applied to generated examples when making predictions from the simulation. We illustrate this approach using GANS trained on standard multimodal probability densities as well as calorimeter simulations from high energy physics. We show that the weighted GAN examples significantly improve the accuracy of the generated samples without a large loss in statistical power. This approach could be applied to any generative model and is a promising refinement method for high energy physics applications and beyond.

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

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

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

[4]  E. Gross,et al.  Efficiency Parameterization with Neural Networks , 2020, Computing and Software for Big Science.

[5]  M. Erdmann,et al.  Adversarial Neural Network-based data-simulation corrections for jet-tagging at CMS , 2020 .

[6]  K. Matchev,et al.  Uncertainties associated with GAN-generated datasets in high energy physics , 2020, SciPost Physics.

[7]  D. Whiteson,et al.  Resonance Searches with Machine Learned Likelihood Ratios , 2020, 2002.04699.

[8]  B. Nachman,et al.  Simulation assisted likelihood-free anomaly detection , 2020, Physical Review D.

[9]  Colin Raffel,et al.  Towards GAN Benchmarks Which Require Generalization , 2020, ICLR.

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

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

[12]  Antonio D. Pereira,et al.  Universal critical behavior in tensor models for four-dimensional quantum gravity , 2019, Journal of High Energy Physics.

[13]  Maurizio Pierini,et al.  Particle Generative Adversarial Networks for full-event simulation at the LHC and their application to pileup description , 2019, Journal of Physics: Conference Series.

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

[15]  Shideh Rezaeifar,et al.  Information bottleneck through variational glasses , 2019, ArXiv.

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

[17]  J. Maalmi,et al.  Fast simulation of muons produced at the SHiP experiment using Generative Adversarial Networks , 2019 .

[18]  Patrick T. Komiske,et al.  OmniFold: A Method to Simultaneously Unfold All Observables. , 2019, Physical review letters.

[19]  S. Ermon,et al.  Fair Generative Modeling via Weak Supervision , 2019, ICML.

[20]  SHiP Collaboration.  Fast simulation of muons produced at the SHiP experiment using Generative Adversarial Networks , 2019, Journal of Instrumentation.

[21]  S. Carrazza,et al.  Lund jet images from generative and cycle-consistent adversarial networks , 2019, The European Physical Journal C.

[22]  K. Cranmer,et al.  MadMiner: Machine Learning-Based Inference for Particle Physics , 2019, Computing and Software for Big Science.

[23]  B. Nachman,et al.  Neural networks for full phase-space reweighting and parameter tuning , 2019, Physical Review D.

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

[25]  Sofia Vallecorsa,et al.  3D convolutional GAN for fast simulation , 2019, EPJ Web of Conferences.

[26]  W. Bhimji,et al.  Next Generation Generative Neural Networks for HEP , 2019, EPJ Web of Conferences.

[27]  Sachin Dev,et al.  Geant4 - A Simulation Toolkit , 2019 .

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

[29]  Nikita Kazeev,et al.  Cherenkov Detectors Fast Simulation Using Neural Networks , 2019, Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment.

[30]  Eric Horvitz,et al.  Bias Correction of Learned Generative Models using Likelihood-Free Importance Weighting , 2019, DGS@ICLR.

[31]  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.

[32]  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.

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

[34]  Dmitry Ulyanov,et al.  Generative Models for Fast Calorimeter Simulation: the LHCb case> , 2018, EPJ Web of Conferences.

[35]  Jason Yosinski,et al.  Metropolis-Hastings Generative Adversarial Networks , 2018, ICML.

[36]  Jan M. Pawlowski,et al.  Reducing autocorrelation times in lattice simulations with generative adversarial networks , 2018, Mach. Learn. Sci. Technol..

[37]  L. Pang,et al.  Regressive and generative neural networks for scalar field theory , 2018, Physical Review D.

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

[39]  Trevor Darrell,et al.  Discriminator Rejection Sampling , 2018, ICLR.

[40]  Sven Krippendorf,et al.  GANs for generating EFT models , 2018, Physics Letters B.

[41]  S. Vallecorsa,et al.  Generative models for fast simulation , 2018, Journal of Physics: Conference Series.

[42]  P. Mendez Lorenzo,et al.  Three dimensional Generative Adversarial Networks for fast simulation , 2018, Journal of Physics: Conference Series.

[43]  Gilles Louppe,et al.  Likelihood-free inference with an improved cross-entropy estimator , 2018, ArXiv.

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

[45]  Jianfeng Feng,et al.  Chi-square Generative Adversarial Network , 2018, ICML.

[46]  T. Trzciński,et al.  Generative Models for Fast Cluster Simulations in the TPC for the ALICE Experiment , 2018, Advances in Intelligent Systems and Computing.

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

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

[49]  Gilles Louppe,et al.  Mining gold from implicit models to improve likelihood-free inference , 2018, Proceedings of the National Academy of Sciences.

[50]  Gilles Louppe,et al.  A guide to constraining effective field theories with machine learning , 2018, Physical Review D.

[51]  Gilles Louppe,et al.  Constraining Effective Field Theories with Machine Learning. , 2018, Physical review letters.

[52]  Jonathan R. Walsh,et al.  Boltzmann Encoded Adversarial Machines , 2018, ArXiv.

[53]  He Ma,et al.  Quantitatively Evaluating GANs With Divergences Proposed for Training , 2018, ICLR.

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

[55]  Michela Paganini,et al.  CaloGAN: Simulating 3D High Energy Particle Showers in Multi-Layer Electromagnetic Calorimeters with Generative Adversarial Networks , 2017, ArXiv.

[56]  Michela Paganini,et al.  Controlling Physical Attributes in GAN-Accelerated Simulation of Electromagnetic Calorimeters , 2017, Journal of Physics: Conference Series.

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

[58]  Léon Bottou,et al.  Wasserstein Generative Adversarial Networks , 2017, ICML.

[59]  Shakir Mohamed,et al.  Variational Approaches for Auto-Encoding Generative Adversarial Networks , 2017, ArXiv.

[60]  Kilian Q. Weinberger,et al.  On Calibration of Modern Neural Networks , 2017, ICML.

[61]  Stefano Ermon,et al.  Flow-GAN: Combining Maximum Likelihood and Adversarial Learning in Generative Models , 2017, AAAI.

[62]  Peter Dayan,et al.  Comparison of Maximum Likelihood and GAN-based training of Real NVPs , 2017, ArXiv.

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

[64]  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.

[65]  Stefano Ermon,et al.  Boosted Generative Models , 2016, AAAI.

[66]  David Lopez-Paz,et al.  Revisiting Classifier Two-Sample Tests , 2016, ICLR.

[67]  Shakir Mohamed,et al.  Learning in Implicit Generative Models , 2016, ArXiv.

[68]  B. Nachman.  Investigating the Quantum Properties of Jets and the Search for a Supersymmetric Top Quark Partner with the ATLAS Detector , 2016, 1609.03242.

[69]  Sebastian Nowozin,et al.  f-GAN: Training Generative Neural Samplers using Variational Divergence Minimization , 2016, NIPS.

[70]  Andy Davis,et al.  This Paper Is Included in the Proceedings of the 12th Usenix Symposium on Operating Systems Design and Implementation (osdi '16). Tensorflow: a System for Large-scale Machine Learning Tensorflow: a System for Large-scale Machine Learning , 2022 .

[71]  Samy Bengio,et al.  Generating Sentences from a Continuous Space , 2015, CoNLL.

[72]  Gilles Louppe,et al.  Approximating Likelihood Ratios with Calibrated Discriminative Classifiers , 2015, 1506.02169.

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

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

[75]  Frank Gaede,et al.  DD4hep: A Detector Description Toolkit for High Energy Physics Experiments , 2014 .

[76]  J. Favereau,et al.  DELPHES 3: a modular framework for fast simulation of a generic collider experiment , 2013, Journal of High Energy Physics.

[77]  Masashi Sugiyama,et al.  Density Ratio Estimation in Machine Learning , 2012 .

[78]  M. Wolter,et al.  TMVA - Toolkit for Multivariate Data Analysis , 2007, physics/0703039.

[79]  Bernhard Schölkopf,et al.  A Kernel Method for the Two-Sample-Problem , 2006, NIPS.

[80]  Eric R. Ziegel,et al.  The Elements of Statistical Learning , 2003, Technometrics.

[81]  Flemming Topsøe,et al.  Some inequalities for information divergence and related measures of discrimination , 2000, IEEE Trans. Inf. Theory.

[82]  Chris Martens,et al.  Theory , 1934, Secrets in Global Governance.

[83]  Fedor Ratnikov,et al.  Generative Models for Fast Calorimeter Simulation.LHCb case , 2018, ArXiv.

[84]  Jinsung Yoon,et al.  GENERATIVE ADVERSARIAL NETS , 2018 .

[85]  Maurizio Pierini,et al.  Calorimetry with Deep Learning : Particle Classification , Energy Regression , and Simulation for High-Energy Physics , 2017 .

[86]  Luke de Oliveira.  Tips and Tricks for Training GANs with Physics Constraints , 2017 .

[87]  Andrew L. Maas.  Rectifier Nonlinearities Improve Neural Network Acoustic Models , 2013 .