Ramon Winterhalder
  • Home
  • Papers
  • Experience
  • Projects
  • Publications
    • FASTColor -- Full-color Amplitude Surrogate Toolkit for QCD
    • Amplitude Uncertainties Everywhere All at Once
    • How to Deep-Learn the Theory behind Quark-Gluon Tagging
    • BitHEP - The Limits of Low-Precision ML in HEP
    • Accurate Surrogate Amplitudes with Calibrated Uncertainties
    • Differentiable MadNIS-Lite
    • Event generators for high-energy physics experiments
    • Full and approximated NLO predictions for like-sign W-boson scattering at the LHC
    • The MadNIS reloaded
    • Precision-Machine Learning for the Matrix Element Method
    • Elsa: enhanced latent spaces for improved collider simulations
    • Like-sign W-boson scattering at the LHC — approximations and full next-to-leading-order predictions
    • Machine learning and LHC event generation
    • MadNIS - Neural multi-channel importance sampling
    • Modern Machine Learning for LHC Physicists
    • Ephemeral Learning - Augmenting Triggers with Online-Trained Normalizing Flows
    • Publishing unbinned differential cross section results
    • Targeting multi-loop integrals with neural networks
    • Latent Space Refinement for Deep Generative Models
    • How to GAN Event Unweighting
    • How to GAN : Novel simulation methods for the LHC
    • How to GAN away Detector Effects
    • How to GAN Event Subtraction
    • Invertible Networks or Partons to Detector and Back Again
    • How to GAN LHC Events
  • Projects
    • MadNIS
    • MadGraph5_aMC@NLO
  • Projects
  • Experience

MadNIS

Nov 10, 2024 · 1 min read
Go to Project Site

MadNIS is a Python library for neural importance sampling based on PyTorch. It will be used for Monte Carlo LHC event generation in future versions of MadGraph5_aMC@NLO.

Last updated on Nov 10, 2024
Neural Importance Sampling Event Generator
Ramon Winterhalder
Authors
Ramon Winterhalder
Assistant Professor
MadGraph5_aMC@NLO Oct 1, 2023 →

© 2025 Ramon Winterhalder