Skip to main content

Mining gold from MadGraph to improve limit setting in particle physics.

Project description

MadMiner: Machine learning–based inference for particle physics

By Johann Brehmer, Felix Kling, Irina Espejo, and Kyle Cranmer

PyPI version Build Status Documentation Status Gitter Docker pulls Code style: black License: MIT DOI

Introduction

Particle physics processes are usually modeled with complex Monte-Carlo simulations of the hard process, parton shower, and detector interactions. These simulators typically do not admit a tractable likelihood function: given a (potentially high-dimensional) set of observables, it is usually not possible to calculate the probability of these observables for some model parameters. Particle physicisists usually tackle this problem of "likelihood-free inference" by hand-picking a few "good" observables or summary statistics and filling histograms of them. But this conventional approach discards the information in all other observables and often does not scale well to high-dimensional problems.

In the three publications "Constraining Effective Field Theories With Machine Learning", "A Guide to Constraining Effective Field Theories With Machine Learning", and "Mining gold from implicit models to improve likelihood-free inference", a new approach has been developed. In a nut shell, additional information is extracted from the simulations that is closely related to the matrix elements that determine the hard process. This "augmented data" can be used to train neural networks to efficiently approximate arbitrary likelihood ratios. We playfully call this process "mining gold" from the simulator, since this information may be hard to get, but turns out to be very valuable for inference.

But the gold does not have to be hard to mine: MadMiner automates these modern multivariate inference strategies. It wraps around the simulators MadGraph and Pythia, with different options for the detector simulation. It streamlines all steps in the analysis chain from the simulation to the extraction of the augmented data, their processing, the training and evaluation of the neural networks, and the statistical analysis are implemented.

Resources

Paper

Our main publication MadMiner: Machine-learning-based inference for particle physics provides an overview over this package. We recommend reading it first before jumping into the code.

Installation instructions

Please have a look at our installation instructions.

Tutorials

In the examples folder in this repository, we provide two tutorials. The first at examples/tutorial_toy_simulator/tutorial_toy_simulator.ipynb is based on a toy problem rather than a full particle-physics simulation. It demonstrates inference with MadMiner without spending much time on the more technical steps of running the simulation. The second, at examples/tutorial_particle_physics, shows all steps of a particle-physics analysis with MadMiner.

Documentation

The madminer API is documented on readthedocs.

Support

If you have any questions, please chat to us in our Gitter community or write us at johann.brehmer@nyu.edu.

Citations

If you use MadMiner, please cite our main publication,

@article{MadMiner,
      author         = "Brehmer, Johann and Kling, Felix and Espejo, Irina and Cranmer, Kyle",
      title          = "{MadMiner: Machine-learning-based inference for particle physics}",
      year           = "2019",
      eprint         = "1907.10621",
      archivePrefix  = "arXiv",
      primaryClass   = "hep-ph",
      SLACcitation   = "%%CITATION = ARXIV:1907.10621;%%"
}

The code itself can be cited as

@misc{MadMiner_code,
      author         = "Brehmer, Johann and Kling, Felix and Espejo, Irina and Cranmer, Kyle",
      title          = "{MadMiner}",
      doi            = "10.5281/zenodo.1489147",
      url            = {https://github.com/diana-hep/madminer}
}

The main references for the implemented inference techniques are the following:

Acknowledgements

We are immensely grateful to all contributors and bug reporters! In particular, we would like to thank Zubair Bhatti, Lukas Heinrich, Alexander Held, and Samuel Homiller.

The SCANDAL inference method is based on Masked Autoregressive Flows, and our implementation is a pyTorch port of the original code by George Papamakarios et al., which is available at https://github.com/gpapamak/maf.

The setup.py was adapted from https://github.com/kennethreitz/setup.py.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

madminer-0.4.9.tar.gz (136.2 kB view hashes)

Uploaded Source

Built Distribution

madminer-0.4.9-py3-none-any.whl (176.8 kB view hashes)

Uploaded Python 3

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page