mlsanityData to 14 Oct 2026

One flow to correct them all: improving simulations in high-energy physics with a single normalising flow and a switch

arXiv 2403.18582 ↗First posted 27 Mar 2024hep-ph cs.LG hep-excited by 4

Not on the map. Why?

Abstract (arXiv)

Simulated events are key ingredients in almost all high-energy physics analyses. However, imperfections in the simulation can lead to sizeable differences between the observed data and simulated events. The effects of such mismodelling on relevant observables must be corrected either effectively via scale factors, with weights or by modifying the distributions of the observables and their correlations. We introduce a correction method that transforms one multidimensional distribution (simulation) into another one (data) using a simple architecture based on a single normalising flow with a boolean condition. We demonstrate the effectiveness of the method on a physics-inspired toy dataset with non-trivial mismodelling of several observables and their correlations.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 19 of its 32 references that are in the map. First posted on arXiv 27 Mar 2024.

Builds on

19 of 32 references.

References · 19

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  2. 2016XGBoost: A Scalable Tree Boosting Systemcited by 5,166
  3. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 5,045
  4. 2018Glow: Generative Flow with Invertible 1x1 Convolutionscited by 1,545
  5. 2019Normalizing Flows for Probabilistic Modeling and Inferencecited by 1,323
  6. 2017Masked Autoregressive Flow for Density Estimationcited by 684
  7. 2019Neural Spline Flowscited by 596
  8. 2016Input Convex Neural Networkscited by 414
  9. 2015MADE: Masked Autoencoder for Distribution Estimationcited by 307
  10. 2016Revisiting Classifier Two-Sample Testscited by 268
  11. 2018Neural Importance Samplingcited by 155
  12. 2015Approximating Likelihood Ratios with Calibrated Discriminative Classifierscited by 90
7 more
  1. 2020Invertible Generative Modeling using Linear Rational Splinescited by 40
  2. 2019Cubic-Spline Flowscited by 35
  3. 2020DCTRGAN: Improving the Precision of Generative Models with Reweightingcited by 22
  4. 2019Neural Networks for Full Phase-space Reweighting and Parameter Tuningcited by 20
  5. 2016Reweighting with Boosted Decision Treescited by 10
  6. 2023Flow Away your Differences: Conditional Normalizing Flows as an Improvement to Reweightingcited by 6
  7. 2021Transport away your problems: Calibrating stochastic simulations with optimal transportcited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 4.

4 papers.

  1. 2026Profiling systematic uncertainties in Simulation-Based Inference with Factorizable Normalizing Flowscited by 2
  2. 2026Factorizable Normalizing Flows for parameter-dependent density morphingcited by 1
  3. 2026Unknown Unknowns: Model Misspecification in Machine Learning for Physicscited by 1
  4. 2026Learning Minimal-Deviation Corrections for Multi-Dimensional Mismodelling in HEP Simulationscited by 0