Sign in

DarkGenerators

Interpretable large scale deep generative models for Dark Matter searches

Dark matter (DM) is five times more abundant in the Universe than visible matter. Yet, its nature remains unknown and constitutes one of the most exciting and complex research questions today. New astrophysical/experimental big volume and high quality data must be matched with tools that are fit for the complex analysis of these data. Recent developments in deep learning and differentiable programming are likely to play a key role in this regard. Differential programming allows the efficient optimisation of a very large number of parameters of a program, e.g. to choose optimal internal or (astro-)physical parameters of a physical simulation. Deep generative models are Machine Learning programs that can generate data and can be used to simulate physical events. Exploring the optimal use, connection and synergy of these two new possibilities is the main goal of this proposal. We concentrate on two exemplary important datasets for DM research: data from the Large Hadron Collider (LHC), and images of strongly lensed galaxies. We will study how to improve the realism of deep generative models, and connect them with the help of differentiable probabilistic programming techniques to build fast, accurate and flexible new analysis pipelines. We explore the use of these pipelines for anomaly detection (to search for new physics), image and parameter reconstruction. A central outcome of our work will be an accessible and extensible public analysis tool that will spread the best of these new techniques to the large community of DM research and beyond.

Participating organisations

Netherlands eScience Center
SURF
University of Amsterdam

Team

AB
Axel Berg
Programme Director
SURF
CW
Christoph Weniger
Principal investigator
University of Amsterdam
FN
Francesco Nattino
eScience Research Engineer
Netherlands eScience Center
Meiert Grootes
Meiert Grootes
Senior eScience Research Engineer
Netherlands eScience Center
Rena Bakhshi
Rena Bakhshi
Programme Manager
Netherlands eScience Center
Sonja Georgievska
Sonja Georgievska
eScience Research Engineer
Netherlands eScience Center

Related projects

PADRE - The PetaFLOP AARTFAAC Data-Reduction Engine

Improving the AARTFAAC processing pipeline

Updated 7 days ago
Running

Scaling up pangenomics for plant breeding

Delivering a pangenome approach that drastically improves the analytical power on plant data

Updated 7 days ago
Running

CORTEX

Self-learning machines hunt for explosions in the universe and speed up innovations in industry and...

Updated 7 days ago
Running

iDark

The intelligent Dark Matter survey

Updated 7 days ago
Finished

Related tools

swyft

SW

swyft is the official implementation of Truncated Marginal Neural Ratio Estimation, a hyper-efficient, simulation-based inference technique for complex data and expensive simulators.

Updated 5 months ago
5