In recent years, AI achieved impressive results in different fields, incl. in computer vision, natural language processing and reinforcement learning. These breakthroughs show how AI will influence and change our daily lives, business and even research in many aspects. With the advent of deep learning and also traditional AI methods, such as AI planning, SAT solving or evolutionary algorithms, a multitude of different techniques are available these days. However, applying these techniques is challenging, and even experienced AI developers are faced with several difficult design decisions, making the development of new AI applications a tedious, error-prone and time-consuming task. Therefore, we develop new approaches to increase efficiency in AI application development by reducing the required expert knowledge, improving development time and reducing chances of error. We do this with democratization of AI and social responsibility in mind.
Prof. Dr. rer. nat. Marius Lindauer


30167 Hannover


Research Interests
Actually, I'm interested in many topics related to AutoML, machine learning, AI and interdisciplinary applications of these. Here are some selected topics:
- Green-AutoML
- Human-centered AutoML
- Dynamic Algorithm Configuration
- Generalization of Reinforcement Learning
- Applications to production or health/medicine
Curriculum Vitae
-
Working Experience
since 2022
Head of Institute of AI, Leibniz University Hannoversince 2019
Professor of Machine Learning, Leibniz University Hannover2017-2019
Lecturer (i.e., "Akademischer Rat"), University of Freiburg2014-2017
PostDoc, University of Freiburg2010-2014
Phd Student, University of Potsdam -
Education
2010-2015
Phd (Dr. rer. nat), University of Potsdam2008-2010
Master of Science, Computer Science, University of Potsdam2005-2008
Bachelor of Science, Computer Science, University of Potsdam -
Selected Awards
- 2022: ERC Starting Grant on ixAutoML
- 2020: 3rd place(*) at the official leaderboard and 1st place at the warmstart friendly leaderboard at the BBO-Challenge at NeurIPS'20 (* after fixing a minor bug)
- 2018: Winner of 2nd AutoML challenge::PAKDD2018 with aad_freibug and PoSH Auto-sklearn
- 2016: Winner of ChaLearn AutoML challenge "AutoML 5" with aad_freibug and auto-sklearn
- 2015: Winner of ICON Challenge on algorithm selection with AutoFolio (track: Par10)
- 2013: Winner of Configurable SAT Solver challenge 2013 with the Potassco team and clasp (tracks: crafted and random)
- 2012: Winner of SAT Challenge 2012 with the Potassco team and clasp (track: hard combinatorial)
- 2011: Winner of Answer Set Programming Competition with the Potassco team and claspfolio (track: NP-Problems)
- 2009: Leopold-von-Buch-Bachelor-Award (Best Bachelor in Natural Sciences 2009 at the University of Potsdam)
-
Memberships
- Co-Head AutoML.org Super Group
- Advisory board member and co-founder COSEAL.net
- L3S Member
- Member and co-founder LUH Data Science Lab
- ELLIS Member
- CLAIRE supporter
- Member of Working Group 1: Technological Enablers and Data Science at Pattform Lernende Systeme
- Member of Benchmarking Network
- Member of IEEE Task Force on Automated Algorithm Design, Configuration and Selection
- Social Media
Publications
2023
Bischl, B., Binder, M., Lang, M., Pielok, T., Richter, J., Coors, S., Thomas, J., Ullmann, T., Becker, M., Boulesteix, A-L., Deng, D., & Lindauer, M. (2023). Hyperparameter Optimization: Foundations, Algorithms, Best Practices and Open Challenges. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery.
2022
Adriaensen, S., Biedenkapp, A., Shala, G., Awad, N., Eimer, T., Lindauer, M., & Hutter, F. (Accepted/In press). Automated Dynamic Algorithm Configuration. Journal of Artificial Intelligence Research.
Benjamins, C., Eimer, T., Schubert, F., Mohan, A., Biedenkapp, A., Rosenhahn, B., Hutter, F., & Lindauer, M. (2022). Contextualize Me -- The Case for Context in Reinforcement Learning.
Benjamins, C., Raponi, E., Jankovic, A., Blom, K. V. D., Santoni, M. L., Lindauer, M., & Doerr, C. (2022). PI is back! Switching Acquisition Functions in Bayesian Optimization. In 2022 NeurIPS Workshop on Gaussian Processes, Spatiotemporal Modeling, and Decision-making Systems
Benjamins, C., Jankovic, A., Raponi, E., Blom, K. V. D., Lindauer, M., & Doerr, C. (2022). Towards Automated Design of Bayesian Optimization via Exploratory Landscape Analysis. In 6th Workshop on Meta-Learning at NeurIPS 2022
Bothmann, L., Strickroth, S., Casalicchio, G., Rügamer, D., Lindauer, M., Scheipl, F., & Bischl, B. (2022). Developing Open Source Educational Resources for Machine Learning and Data Science. In Teaching Machine Learning Workshop at ECML 2022
Deng, D., Karl, F., Hutter, F., Bischl, B., & Lindauer, M. (2022). Efficient Automated Deep Learning for Time Series Forecasting. In Proceedings of the European Conference on Machine Learning (ECML)
Deng, D., & Lindauer, M. (2022). Searching in the Forest for Local Bayesian Optimization. In ECML/PKDD workshop on Meta-learning
Feurer, M., Eggensperger, K., Falkner, S., Lindauer, M. T., & Hutter, F. (2022). Auto-Sklearn 2.0: Hands-free AutoML via Meta-Learning. Journal of Machine Learning Research.
Hvarfner, C., Stoll, D., Souza, A. L. F., Lindauer, M., Hutter, F., & Nardi, L. (2022). $\pi$ BOAugmenting Acquisition Functions with User Beliefs for Bayesian Optimization. In Proceedings of the International conference on Learning Representation (ICLR)
Lindauer, M., Eggensperger, K., Feurer, M., Biedenkapp, A., Deng, D., Benjamins, C., Sass, R., & Hutter, F. (2022). SMAC3: A Versatile Bayesian Optimization Package for Hyperparameter Optimization. Journal of Machine Learning Research.
Mallik, N., Hvarfner, C., Stoll, D., Janowski, M., Bergman, E., Lindauer, M. T., Nardi, L., & Hutter, F. (2022). PriorBand: HyperBand + Human Expert Knowledge. In 2022 NeurIPS Workshop on Meta Learning (MetaLearn)
Mohan, A., Ruhkopf, T., & Lindauer, M. (2022). Towards Meta-learned Algorithm Selection using Implicit Fidelity Information. In ICML Workshop on Adaptive Experimental Design and Active Learning in the Real World (ReALML)
Moosbauer, J., Casalicchio, G., Lindauer, M., & Bischl, B. (2022). Enhancing Explainability of Hyperparameter Optimization via Bayesian Algorithm Execution.
Parker-Holder, J., Rajan, R., Song, X., Biedenkapp, A., Miao, Y., Eimer, T., Zhang, B., Nguyen, V., Calandra, R., Faust, A., Hutter, F., & Lindauer, M. (2022). Automated Reinforcement Learning (AutoRL): A Survey and Open Problems. Journal of Artificial Intelligence Research.
Ruhkopf, T., Mohan, A., Deng, D., Tornede, A., Hutter, F., & Lindauer, M. (2022). MASIF: Meta-learned Algorithm Selection using Implicit Fidelity Information.
Sass, R., Bergman, E., Biedenkapp, A., Hutter, F., & Lindauer, M. (2022). DeepCAVE: An Interactive Analysis Tool for Automated Machine Learning. In ICML Workshop on Adaptive Experimental Design and Active Learning in the Real World (ReALML)
Schubert, F., Benjamins, C., Döhler, S., Rosenhahn, B., & Lindauer, M. (2022). POLTER: Policy Trajectory Ensemble Regularization for Unsupervised Reinforcement Learning.
2021
Benjamins, C., Eimer, T., Schubert, F., Biedenkapp, A., Rosenhahn, B., Hutter, F., & Lindauer, M. (2021). CARL: A Benchmark for Contextual and Adaptive Reinforcement Learning. In Workshop on Ecological Theory of Reinforcement Learning, NeurIPS 2021
Biedenkapp, A., Rajan, R., Hutter, F., & Lindauer, M. (2021). TempoRL: Learning When to Act. In Proceedings of the international conference on machine learning (ICML)
Projects
-
Dynamic Algorithm ConfigurationDa die Konfigurationen während der Laufzeit in Abhängigkeit vom aktuellen Zustand des Algorithmus ausgewählt werden sollten, kann es als ein Problem des Reinforcement Learning (RL) betrachtet werden, bei dem ein Agent in jedem Zeitschritt die zu verwendende Konfiguration auf der Grundlage der Leistung im letzten Schritt und des aktuellen Zustands des Algorithmus auswählt. Dies ermöglicht uns einerseits den Einsatz leistungsfähiger RL-Methoden, andererseits bringt RL auch eine Reihe von Herausforderungen mit sich, wie Instabilität, Rauschen und Ineffizienz bei der Abtastung, die bei Anwendungen wie DAC angegangen werden müssen. Daher umfasst die Forschung zu DAC auch die Forschung zu zuverlässigem, interpretierbarem, allgemeinem und schnellem Reinforcement Learning.Led by: Prof. Dr. Marius LindauerYear: 2019Funding: DFGDuration: 2019-2023
-
Dynamic Algorithm ConfigurationAs configurations should be chosen during runtime depending on the current algorithm state, it can be viewed as a reinforcement learning (RL) problem where at each timestep an agent selects the configuration to use based on the performance in the last step and the current state of the algorithm. This enables us to use powerful RL methods on one hand; on the other, RL also brings a set of challenges like instability, noise and sample inefficiency that need to be addressed in applications such as DAC. Therefore research on DAC also includes research on reliable, interpretable, general and fast reinforcement learning.Led by: Prof. Dr. Marius LindauerYear: 2019Funding: DFGDuration: 2019-2023
-
CoyPu: Cognitive Economy Intelligence Plattform für die Resilienz wirtschaftlicher ÖkosystemeNaturkatastrophen, Pandemien, Finanzkrisen, politische Krisen und Angebotsknappeheiten oder Nachfrageschocks propagieren sich durch offensichtliche und latente Handelsbeziehungen durch das globale ökonomische System. Dies ist eine Konsequenz der kontinuierlichen Globalisierung mit der einhergehenden Arbeitsteilung. Ziel dieses Projektes ist es diese Verbindungen offenzulegen und kaskadierende Risiken vorherzusagen um damit Unternehmen die Möglichkeit einzuräumen vorausschauend agieren zu können.Led by: Prof. Marius Lindauer and Prof. Maria Esther-Vidal (L3S/LUH)Team:Year: 2021Funding: Innovationswettbewerb Künstliche Intelligenz (BMWK)Duration: 2021-2024
-
Leibniz AI AcademyThe Leibniz AI Academy aims to develop and establish a trans-curricular and interdisciplinary micro-degree program at the Leibniz Universität Hannover (LUH), in which students from different courses of study acquire competencies in the field of Artificial IntelligenceLed by: Prof. Dr. Marius Lindauer, Prof. Dr. Ralph Ewert, Prof. Dr. Johannes KrugelYear: 2021Funding: Bundesministerium für Bildung und Forschung (BMBF)Duration: 2021 - 2024
-
ERC Starting Grant: Interactive and Explainable Human-Centered AutoMLTrust and interactivity are key factors in the future development and use of automated machine learning (AutoML), supporting developers and researchers in determining powerful task-specific machine learning pipelines, including pre-processing, predictive algorithm, their hyperparameters and--if applicable--the architecture design of deep neural networks. Although AutoML is ready for its prime time after it achieved impressive results in several machine learning (ML) applications and its efficiency improved by several orders of magnitudes in recent years, democratization of machine learning via AutoML is still not achieved. In contrast to previously purely automation-centered approaches, ixAutoML is designed with human users at its heart in several stages. First of all, the foundation of trustful use of AutoML will be based on explanations of its results and processes. Therefore, we aim for: (i) Explaining static effects of design decisions in ML pipelines optimized by state-of-the-art AutoML systems. (ii) Explaining dynamic AutoML policies for temporal aspects of dynamically adapted hyperparameters while ML models are trained. These explanations will be the base for allowing interactions, bringing the best of two worlds together: human intuition and generalization capabilities for complex systems, and efficiency of systematic optimization approaches for AutoML. Concretely, we aim for: (iii) Enabling interactions between humans and AutoML by taking human's latent knowledge into account and learning when to interact. (iv) Building first ixAutoML prototypes and showing its efficiency in the context of Industry 4.0. Perfectly aligned with the EU's AI strategy and recent efforts on interpretability in the ML community, we strongly believe that this timely human-centered ixAutoML will have a substantial impact on the democratization of machine learning.Led by: Prof. Dr. Marius LindauerTeam:Year: 2022Funding: EUDuration: 2022-2027
-
KISSKI: AI Service CenterThe central approach for the KISSKI project is the research on AI methods and their provision with the goal of enabling a highly available AI service center for critical and sensitive infrastructures with a focus on the fields of medicine and energy. Due to their relevance to society as a whole, medicine and the energy industry are among the future fields of application-oriented AI research in Germany. Beyond the technological developments, artificial intelligence (AI) has the potential to make a significant contribution to social progress. This is particularly true in areas where digitization processes are increasingly gaining ground and complexity is high. For both medicine and the energy industry, the pressure to innovate, but also the potential, is immense due to the availability of more and more distributed information based on a multitude of new sensors and actuators. The increasing complexity of the tasks as well as the availability of very large data sets offer a high potential for the application of AI methods in both topics.Led by: Prof. Dr. Marius LindauerTeam:Year: 2022Funding: BMBFDuration: 2022-2025