As a research scientist at Qualcomm AI Research Amsterdam, I am interested in causality, representation learning, and interactive learning. Before that, I was a postdoc in Kyle Cranmer's group at NYU, working on the intersection of machine learning and physics. My background is in particle physics, I got my PhD in Tilman Plehn's group at Heidelberg University.
He / him.
I find it interesting to imbue machine learning models with structure, usually based on human knowledge of the underlying laws of nature or the symmetries of a system. One flavour of this is simulation-based inference, which combines expert-designed simulators and neural surrogate models. Another one are latent variable models with structured latent spaces. Lately I have been interested in causality, in particular causal representation learning, and how that can help us solve practical problems in interactive learning.
You can find a more or less complete list of my papers on Google Scholar. Here I want to highlight a few favorites:
Weakly supervised causal representation learning.
Johann Brehmer, Pim de Haan, Phillip Lippe, and Taco Cohen.
NeurIPS 2022.
[arXiv]
[bibtex]
Instance-adaptive video compression: Improving neural codecs by training on the test set.
Ties van Rozendaal, Johann Brehmer, Yunfan Zhang, Reza Pourreza, and Taco Cohen.
Under review (2022).
[arXiv]
[bibtex]
Flows for simultaneous manifold learning and density estimation.
Johann Brehmer and Kyle Cranmer.
NeurIPS 2020.
[arXiv]
[conference]
[bibtex]
[code]
The frontier of simulation-based inference.
Kyle Cranmer, Johann Brehmer, and Gilles Louppe.
Proceedings of the National Academy of Science 117 (2020).
[arXiv]
[journal]
[bibtex]
Simulation-based inference methods for particle physics.
Johann Brehmer and Kyle Cranmer.
Book chapter in Artificial Intelligence for High-Energy Physics (World Scientific, 2022).
[arXiv]
[book]
[bibtex]
Mining for Dark Matter Substructure: Inferring subhalo population properties from strong lenses with machine learning.
Johann Brehmer, Siddharth Mishra-Sharma, Joeri Hermans, Gilles Louppe, and Kyle Cranmer.
The Astrophysical Journal 886 (2019).
[arXiv]
[journal]
[bibtex]
[code]
MadMiner: Machine learning-based inference for particle physics.
Johann Brehmer, Felix Kling, Irina Espejo, and Kyle Cranmer.
Computing and Software for Big Science 4 (2020).
[arXiv]
[journal]
[bibtex]
[code]
Mining gold from implicit models to improve likelihood-free inference.
Johann Brehmer, Gilles Louppe, Juan Pavez, and Kyle Cranmer.
Proceedings of the National Academy of Science 117 (2020).
[arXiv]
[journal]
[bibtex]
Constraining effective field theories with machine learning.
Johann Brehmer, Kyle Cranmer, Gilles Louppe, and Juan Pavez.
Physical Review Letters 121 (2018).
[arXiv]
[journal]
[bibtex]
[code]
A guide to constraining effective field theories with machine learning.
Johann Brehmer, Kyle Cranmer, Gilles Louppe, and Juan Pavez.
Physical Review D 98 (2018).
[arXiv]
[journal]
[bibtex]
[code]
Hierarchical clustering in particle physics through reinforcement learning.
Johann Brehmer, Sebastian Macaluso, Duccio Pappadopulo, and Kyle Cranmer.
NeurIPS workshop on Machine Learning and the Physical Sciences (2020).
[arXiv]
[workshop]
[bibtex]
[code]
Better Higgs Measurements Through Information Geometry.
Johann Brehmer, Kyle Cranmer, Felix Kling, Tilman Plehn.
Physical Review D 95 (2017).
[arXiv]
[journal]
[bibtex]
Together with Felix Kling, Irina Espejo, Sinclert Perez, and Kyle Cranmer, I have developed the MadMiner library, which automates machine learning–powered simulation-based inference techniques for particle physics experiments.
My GitHub page contains the code used for most of my pre-Qualcomm papers.
Over the years, I had a lot of fun presenting our research in different places. See this repository for a list and PDF versions of my slides. I'm always happy to talk about our recent papers.
Write me at jbrehmer@qti.qualcomm.com (work) mail@johannbrehmer.de (personal), or come visit me in Amsterdam!
I like travelling and taking pictures.
Iceland, September 2022.
Iceland, September 2022.
Iceland, August 2022.
Iceland, August 2022.
Iceland, August 2022.
January 2022.
Amsterdam, September 2021.
...around Lisse, May 2021.
Amsterdam, March 2021.
Before sunrise on a rare snowy day in Amsterdam, February 2021.
Amsterdam, New Year's Eve 2020/2021.
September 2020.
Montelobos Espadin, Amaro Sfumato Rabarbaro, Carpano Antica Formula, coldbrew, maple syrup. March 2020.
Thousands of torii at this Shinto shrine in Kyoto, Japan. February 2020.
The bamboo forest in Arashiyama, Japan. February 2020.
Brooklyn Bridge, Jane's Carousel, and the FiDi skyline seen from Manhattan Bridge. January 2020.
A bison chilling in Yellowstone National Park. September 2019.
The Grand Tetons at Oxbow Bend just before sunrise. September 2019.
On the way to Laguna de Los Tres at the base of Mount Fitz Roy. Patagonia, December 2018.
A lone penguin on a beach at the end of the world. Patagonia, December 2018.
Patagonia, December 2018.
Fourth of July 2018, New York.
New York 2018.
The skyline of downtown NYC, as seen from New Jersey's Liberty State Park in 2018.
The NYC skyline as seen from New Jersey, just before sunrise. 2017.
The Milky Way rising over Bear Lake, Rocky Mountain National Park. 2016.
The silhouette of Balanced Rock in Arches National Park in front of the Milky Way and the first glow from the rising moon. 2016.
Chicago's skyline after sunset. 2016.
A plane passing in front of the sun during a solar eclipse seen from Heidelberg. 2015.
A bored macaque behind the wall of a Hindu temple in Sangeh, Bali. 2014.
Java's volcano Bromo shortly before sunrise. Above the crater, a shooting star from the Perseid shower can be seen. 2014.
The view from Heidelberg castle at sunset. Easter 2014.
Paris, 2011.