Marius Hobbhahn

Email
marius.hobbhahn[at]gmail.com

Research Interests

Uncertainty Quantification in Deep Learning
Bayesian Inference
Bayesian Deep Learning
AI Safety and Alignment
Fairness in Machine Learning

Education

International Max-Planck Research School Tübingen, Germany

PhD with Philipp Hennig, 2020-now
Topic: Development of a new approximate inference scheme

University of Tübingen, Germany

M.Sc., Machine Learning/Computer Science, 2018-2020
Grade (1.5)

University of Tübingen, Germany

B.Sc., Computer Science, 2016-2019
Grade: 1.7 (3.3 GPA equivalent)

University of Tübingen, Germany

B.Sc., Cognitive Science, 2015-2018
Grade: 1.8 (3.2 GPA equivalent)

Willstätter Gymnasium Nürnberg, Germany

Abitur, 2007 - 2015
Grade: 1.4 (3.6 GPA equivalent)

Publications

Fast Predictive Uncertainty for Classification with Bayesian Deep Networks

Hobbhahn, Marius; Kristiadi, Agustinus and Hennig, Philipp. arXiv preprint arXiv:2003.01227 (2020).
[arxiv] [code (soon)] [ href='http://www.mariushobbhahn.com/2020-11-03-LB_for_BNNs/'>Blog post]

Sequence Classification using Ensembles of Recurrent Generative Expert Modules

Hobbhahn, Marius; Butz, Martin; Fabi, Sarah and Otte, Sebastian. ESANN (2020).
[(ESANN is postponed to 10/2020)] [code]

ML Experience

Object Detection using the Scattering Transform (Grade: 1.7)

[pdf] [code]

Inverse Classification using Generative Models (Grade: 1.3)

[pdf] [code]

Reconstruction of the Paper "Reading Scene Text in Deep Convolutional Sequences" (Grade: 1.3)

[arxiv] [code]

Bayesian Prediction of Winprobability in League of Legends (Grade: 1.0)

[html] [code]

Additional Information

Successfully completed over 20 lectures related to ML, AI, NNs, RL, Stats, etc. at the University of Tübingen

Programming Experience

Programming Languages: Python > R > Java, JavaScript, C++, SQL, Julia, Flutter
ML related: Pytorch, Tensorflow, Keras, Cuda

Language

English (C2 = IELTS 8.0)
French (B2)
German (native)

Miscellaneous

Academia

  • Participated at multiple ML Summer Schools and conferences including: PAISS2019, ICML2020, GPSS2020, ESANN2020
  • Organized an ML master overview for 9 European Universities [link]

Debating

  • Broke at 35+ tournaments, were in the top 10 speakers 20+ times and won 10 of them.
  • My most prestigious speaker achievements include: 3x breaking ESL at EUDC, Winning Tilbury 2019 and Doxbridge 2020 (Oxford final), Winning 2 Campus Debatten and the Southern German Championship, breaking as 3rd (2018), 2nd (2019) and 1st (2020) team at the German National Championships (DDM) and being best speaker and grand finalist at the DDM 2020
  • Broke at 15+ tournaments as adjudicator and chaired 5+ finals. I chief-adjudicated 10+ tournaments.

Effective Altruism

  • Co-found the Tübingen EA chapter in 2016
  • Co-found the Tübingen AI safety reading group in 2020 (currently inactive)
  • Organized an ML master overview for 9 European Universities [link]
  • Attended multiple EA conferences including: Five worlds collide Vienna (2016), Sentience Conference Berlin (2017), EAGx Utrecht (2018), EAG London (2019)