Mirko Bunse
Postdoctoral Researcher at TU Dortmund University
Bielefeld, North Rhine-Westphalia, Germany
Summary
👤
Senior🎓
Top SchoolMirko Bunse is a postdoctoral researcher with nine years of experience at the intersection of machine learning foundations and astro-particle physics, currently based at the Lamarr Institute in Bielefeld. He develops methods for class prevalence estimation, learning under class-conditional label noise, unsupervised domain adaptation, and active control of simulations—research driven by highly imbalanced, simulation-heavy physics data. With a PhD and MSc from TU Dortmund, he blends rigorous theoretical work with practical needs of experimental physics, including cross-disciplinary collaborations like quantification-unfolding integration. Mirko’s background spans academia and industry software development, giving him fluency in both research and production-oriented engineering. He is particularly skilled at turning domain constraints (sim-to-real gaps, extreme class imbalance) into methodological advances rather than mere nuisances. Colleagues value his knack for steering simulation design strategically to yield more informative training data.
10 years of coding experience
3 years of employment as a software developer
Bachelor of Science - BS, Computer Science, Bachelor of Science - BS, Computer Science at Paderborn UniversityDoctor of Philosophy - PhD, Computer Science, Doctor of Philosophy - PhD, Computer Science at TU Dortmund University
German, English, Italian, French
Stackoverflow
1reputation
0reached
0answers
0questions
Github Skills (66)
deconvolution10
classification10
julia9
tikz9
machine-learning9
hypothesis-tests9
parsing9
parse9
configuration-file9
hypothesis-testing9
full-stack9
scene8
latex8
yaml8
statistics8
Programming languages (9)
Github contributions (5)
mirkobunse/qunfold
Dec 2022 - Feb 2023
A unified implementation of quantification and unfolding algorithms
Contributions:5 releases, 2 reviews, 24 commits in 1 month
mirkobunse/CherenkovDeconvolution.py
May 2018 - Oct 2022
Deconvolution algorithms for Cherenkov astronomy and other use cases
Contributions:86 commits, 1 PR, 26 pushes in 4 years 5 months
deconvolution
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.