Jakob Weissteiner
|
Research Interests
Machine Learning, Deep Learning, Probabilistic AI, Combinatorial Auctions, Market Design, Preference Elicitation
Short Bio
Since February 2019, Jakob is a Ph.D. student advised by Prof. Sven Seuken in the Computation and Economics Research Group at the Department of Informatics of the University of Zurich, where he works on machine learning-based market design.
Jakob received a B.Sc. (2015) and a M.Sc. (2018) in Mathematics from the Technical University of Vienna (specialization: Financial and Actuarial Mathematics). Additionally he received a M.Sc. (2018) in Quantitative Finance from the Vienna University of Economics and Business.
Since September 2021 he is a ETH AI Center affiliated PhD student.
Besides his studies, Jakob was as Workflow Chair part of the organizing committee of the twenty-third ACM Conference on Economics and Computation (EC'22), he worked in the Advanced Analytics team of the Raiffeisen Bank International as a data scientist. From September 2019 until March 2022, he was a board member of the Club Alpbach Zürich.
Publications
- Deep Learning-powered Iterative Combinatorial Auctions.
Jakob Weissteiner and Sven Seuken.
In Proceedings of the Thirty-fourth AAAI Conference on Artificial Intelligence (AAAI '20), New York, USA, February 2020.
Working paper version from Oct 2020: [pdf] [code] - Fourier Analysis-based Iterative Combinatorial Auctions.
Jakob Weissteiner*, Chris Wendler*, Sven Seuken, Ben Lubin, and Markus Püschel.
In Proceedings of the Thirty-first International joint Conference on Artificial Intelligence (IJCAI '22), Vienna, AUT, July 2022.
Full paper version including appendix: [pdf] [code] - Monotone-Value Neural Networks: Exploiting Preference Monotonicity in Combinatorial Assignment
Jakob Weissteiner*, Jakob Heiss*, Julien Siems* and Sven Seuken.
In Proceedings of the Thirty-first International joint Conference on Artificial Intelligence (IJCAI '22), Vienna, AUT, July 2022.
Full paper version including appendix: [pdf] [code] - NOMU: Neural Optimization-based Model Uncertainty
Jakob Weissteiner*, Hanna Wutte*, Jakob Heiss*, Sven Seuken, and Josef Teichmann.
In Proceedings of the Thirty-ninth International Conference on Machine Learning (ICML '22), Baltimore, USA, July 2022.
Full paper version including appendix: [pdf] [code] - Bayesian Optimization-based Combinatorial Assignment
Jakob Weissteiner*, Jakob Heiss*, Julien Siems* and Sven Seuken
In Proceedings of the Thirty-seventh AAAI Conference on Artificial Intelligence (AAAI'23), Washington, D.C., USA, February 2023.
Full paper version including appendix: [pdf] [code]
*These authors contributed equally
Working Papers
- Machine Learning-powered Course Allocation.
Ermis Soumalias*, Behnoosh Zamanlooy*, Jakob Weissteiner and Sven Seuken.
ArXiv preprint: [pdf]
Master's Theses
- Variable importance measures in classification and regression methods.
Jakob Weissteiner. Master's Thesis. Vienna University of Economics and Business, Austria, Sep 2018. [pdf] (PDF, 1 MB) - Über die Orderbuchmodellierung mit Markovschen Ketten in stetiger Zeit.
Jakob Weissteiner. Master's Thesis. Technical University of Vienna, Austria, Jan 2018. [pdf] (PDF, 2 MB)
Curriculum Vitae
Teaching
2021: Head teaching assistant for lecture Market Design and Machine Learning
Head teaching assistant for lecture Seminar: Advanced Topics in Economics and Computation
2020: Head teaching assistant for lecture Seminar: Advanced Topics in Economics and Computation
2019: Teaching assistant for lecture Economics and Computation
Head teaching assistant for Seminar: Advanced Topics in Economics and Computation.
2018: Teaching assistant for lecture Economics and Computation
Teaching assistant for lecture Mathematics II, Vienna University of Economics and Business.
2017: Teaching assistant for lecture Probability Theory, Vienna University of Economics and Business.
2016: Teaching assistant for lecture Risk Management in Finance and Insurance, Technical University of Vienna.
Advised Theses
- Bayesian Optimization with Neural Networks
Master Thesis by Marius Högger, Fall 2020