Ausgewählte Publikationen von Prof. Dr. Marius Lindauer

Kategorie A*

• Matthias Feurer, Katharina Eggensperger, Stefan Falkner, Marius Lindauer,  Frank Hutter Auto-Sklearn 2.0: Hands-free AutoML via Meta-Learning. J. Mach. Learn. Res. (JMLR) 23:1-61 (2022)
  https://doi.org/10.48550/arXiv.2007.04074
• Marius Lindauer, Katharina Eggensperger, Matthias Feurer, André Biedenkapp, Difan Deng, Carolin Benjamins, Tim Ruhkopf, René Sass, Frank Hutter: SMAC3: A Versatile Bayesian Optimization Package for Hyperparameter Optimization. J. Mach. Learn. Res. (JMLR) 23: 54:1-54:9 (2022)
  https://doi.org/10.48550/arXiv.2109.09831
• Steven Adriaensen, André Biedenkapp, Gresa Shala, Noor H. Awad, Theresa Eimer, Marius Lindauer, Frank Hutter: Automated Dynamic Algorithm Configuration. J. Artif. Intell. Res. (JAIR) 75: 1633-1699 (2022)
  https://doi.org/10.48550/arXiv.2205.13881
• Carl Hvarfner, Danny Stoll, Artur L. F. Souza, Marius Lindauer, Frank Hutter, Luigi Nardi: $\pi$BO: Augmenting Acquisition Functions with User Beliefs for Bayesian Optimization. Proceedings of the international conference of learning representations (ICLR) 2022
  https://doi.org/10.48550/arXiv.2204.11051
• Lucas Zimmer, Marius Lindauer, Frank Hutter: Auto-Pytorch: Multi-Fidelity MetaLearning for Efficient and Robust AutoDL. IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI) 43(9): 3079-3090 (2021)
  DOI: 10.1109/TPAMI.2021.3067763
• Arlind Kadra, Marius Lindauer, Frank Hutter, Josif Grabocka: Well-tuned Simple Nets Excel on Tabular Datasets. Proceedings of the international conference on neural information processing systems (NeurIPS) 2021: 23928-23941
  https://doi.org/10.48550/arXiv.2106.11189
• Julia Moosbauer, Julia Herbinger, Giuseppe Casalicchio, Marius Lindauer, Bernd Bischl: Explaining Hyperparameter Optimization via Partial Dependence Plots. Proceedings of the international conference on neural information processing systems (NeurIPS) 2021: 2280-2291
  https://doi.org/10.48550/arXiv.2111.04820
• André Biedenkapp, Raghu Rajan, Frank Hutter, Marius Lindauer: TempoRL: Learning When to Act. Proceedings of the international conference on machine learning (ICML) 2021: 914-924
  https://doi.org/10.48550/arXiv.2106.05262
• Theresa Eimer, André Biedenkapp, Frank Hutter, Marius Lindauer: Self-Paced Context Evaluation for Contextual Reinforcement Learning. Proceedings of the international conference on machine learning ICML 2021: 2948-2958
  https://doi.org/10.48550/arXiv.2106.05110
• Lior Fuks, Noor H. Awad, Frank Hutter, Marius Lindauer: An Evolution Strategy with Progressive Episode Lengths for Playing Games. Proceedings of the international joint conference on AI (IJCAI) 2019: 1234-1240
  https://doi.org/10.24963/ijcai.2019/172

Kategorie B*

• SMAC3: Versatile Bayesian Optimization Package for Hyperparameter Optimization. About 50k downloads via PyPi each month. From 2015-2018, lead developer. From 2019 onwards, project lead (supervision and project administration)
   
• Auto-Sklearn: Automated machine learning toolkit and a drop-in replacement for a scikit-learn estimator. About 7.200 stars on GitHub and, each month, about 32.000 downloads via PyPi. From 2015 onwards, co-supervisor
   
• Auto-PyTorch: An AutoML package for deep learning on tabular data. About 2.100 stars on GitHub. From 2018 onwards, co-supervisor and project administrator
   
• Together with my co-authors, I applied for 12 patents since 2018
   
• Hector Mendoza, Aaron Klein, Matthias Feurer, Jost Tobias Springenberg, Matthias Urban, Michael Burkart, Maximilian Dippel, Marius Lindauer, Frank Hutter: Towards Automatically-Tuned Deep Neural Networks. Automated Machine Learning 2019: 135-149. Book chapter of “AutoML: Methods, Systems, Challenges” Writing original draft and supervision