Porträt von Prof. Dr. rer. nat. Marius Lindauer mit Brille, weißem Hemd und Anhänger-Halskette, lächelnd vor einem hellgrauen Hintergrund. Porträt von Prof. Dr. rer. nat. Marius Lindauer mit Brille, weißem Hemd und Anhänger-Halskette, lächelnd vor einem hellgrauen Hintergrund. © M4 Fotostudio Mirja John
Prof. Dr. rer. nat. Marius Lindauer
Adresse
Welfengarten 1
30167 Hannover
Gebäude
Raum
Porträt von Prof. Dr. rer. nat. Marius Lindauer mit Brille, weißem Hemd und Anhänger-Halskette, lächelnd vor einem hellgrauen Hintergrund. Porträt von Prof. Dr. rer. nat. Marius Lindauer mit Brille, weißem Hemd und Anhänger-Halskette, lächelnd vor einem hellgrauen Hintergrund. © M4 Fotostudio Mirja John
Prof. Dr. rer. nat. Marius Lindauer
Adresse
Welfengarten 1
30167 Hannover
Gebäude
Raum

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.

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

Publications

First 1 2 3 4 5 6 7 8 Last

2026


Benjamins, C., Graf, H., Segel, S., Deng, D., Ruhkopf, T., Hennig, L., Basu, S., Mallik, N., Bergman, E., Chen, D., Clement, F., Tornede, A., Feurer, M., Eggensperger, K., Hutter, F., Doerr, C., & Lindauer, M. (2026). carps: A Framework for Comparing N Hyperparameter Optimizers on M Benchmarks. Transactions on Machine Learning Research. Vorzeitige Online-Publikation. https://doi.org/10.48550/arXiv.2506.06143
Che, M., Tseng, T.-Y., Eimer-Rüegg, T., Lindauer, M., & von Rohr, A. (Angenommen/Im Druck). Efficient Heteroscedastic Bayesian Optimization for Risk-Aware AutoRL. Beitrag in 3rd Reinforcement Learning Conference 2026, RLC'26, Montréal, Kanada.
Deng, D., Winje, A. B., Fehring, L., & Lindauer, M. (2026). Neural Attention Search Linear: Towards Adaptive Token-Level Hybrid Attention Models. in Proceedings of NeurIPS Vorzeitige Online-Publikation. https://arxiv.org/pdf/2602.03681
Fehring, L., Wever, M., Spliethöver, M., Hennig, L., Wachsmuth, H., & Lindauer, M. (2026). Dynamic Priors in Bayesian Optimization for Hyperparameter Optimization. in Proceedings of the AutoML Conference Vorzeitige Online-Publikation. https://doi.org/10.48550/arXiv.2511.02570
Mahlau, Y., Augenstein, Y., Hughes, T., Lindauer, M., & Rosenhahn, B. (2026). Gradient-Informed Bayesian and Interior Point Optimization for Efficient Inverse Design in Nanophotonics. Optics Express, 34(13), 23160-23174. https://doi.org/10.1364/OE.600198
Mladenovic, S., Lindauer, M., & Doerr, C. (2026). Automated Data Preparation for Machine Learning: A Survey. Data-centric Machine Learning Research. Vorzeitige Online-Publikation. https://openreview.net/forum?id=Euti6LHIOs
Pierro, A., Yik, J., Timcheck, J., Lindauer, M., Hüllermeier, E., & Wever, M. D. (2026). Evolutionary Mapping of Neural Networks to Spatial Accelerators. in GECCO '26: Proceedings of the Genetic and Evolutionary Computation Conference (S. 329-337) https://doi.org/10.1145/3795095.3805135
Rook, J., Benjamins, C., Bossek, J., Trautmann, H., Hoos, H., & Lindauer, M. (2026). MO-SMAC: Multi-objective Sequential Model-based Algorithm Configuration. Evolutionary computation, 34(1), 29-52. https://doi.org/10.1162/evco_a_00371
Theodorakopoulos, D., Wever, M., & Lindauer, M. (2026). Dynamic Hyperparameter Importance for Efficient Multi-Objective Optimization. Vorzeitige Online-Publikation. https://doi.org/10.48550/arXiv.2601.03166
Wever, M. D., Muschalik, M., Fumagalli, F., & Lindauer, M. (Angenommen/Im Druck). HyperSHAP: Shapley Values and Interactions for Explaining Hyperparameter Optimization. in Proceedings of the Fortieth AAAI Conference on Artificial Intelligence (AAAI 2026)

2025


Becktepe, J., Hennig, L., Oeltze-Jafra, S., & Lindauer, M. (Angenommen/Im Druck). Auto-nnU-Net: Towards Automated Medical Image Segmentation. in International Conference on Automated Machine Learning 2025 https://openreview.net/pdf?id=XSTIEVoEa2
Deng, D., & Lindauer, M. (2025). Neural Attention Search. in The Thirty-Ninth Annual Conference on Neural Information Processing Systems Vorzeitige Online-Publikation. https://doi.org/10.48550/arXiv.2502.13251
Deng, D., & Lindauer, M. (2025). Optimizing Time Series Forecasting Architectures: A Hierarchical Neural Architecture Search Approach. Transactions on Machine Learning Research, 2025-October. Vorzeitige Online-Publikation. https://doi.org/10.48550/arXiv.2406.05088
Dierkes, J., Eimer, T., Lindauer, M., & Hoos, H. (2025). Performance Prediction In Reinforcement Learning: The Bad And The Ugly. in 18th European Workshop on Reinforcement Learning (EWRL) Vorzeitige Online-Publikation. https://openreview.net/pdf?id=L9J6Xmta4J
Eimer, T., Schäpermeier, L., Biedenkapp, A., Tornede, A., Kotthoff, L., Leyman, P., Feurer, M., Eggensperger, K., Maile, K., Tornede, T., Kozak, A., Xue, K., Wever, M. D., Baratchi, M., Pulatov, D., Trautmann, H., Kashgarani, H., & Lindauer, M. (2025). Best Practices For Empirical Meta-Algorithmic Research: Guidelines from the COSEAL Research Network. Vorzeitige Online-Publikation. https://doi.org/10.48550/arXiv.2512.16491
Fehring, L., Eimer, T., & Lindauer, M. (Angenommen/Im Druck). Growing with Experience: Growing Neural Networks in Deep Reinforcement Learning. in 2025 Multi-disciplinary Conference on Reinforcement Learning and Decision Making (RLDM 2025)
Fehring, L., Wever, M., Spliethöver, M., Hennig, L., Wachsmuth, H., & Lindauer, M. (2025). Towards Dynamic Priors in Bayesian Optimization for Hyperparameter Optimization. in Workshop Track of the AutoML Conference https://openreview.net/pdf?id=mQ0IENZRx2
Graf, H., Fehring, L., Tornede, T., Tornede, A., Wever, M. D., & Lindauer, M. (2025). Towards Exploiting Early Termination for Multi-Fidelity Hyperparameter Optimization. in Workshop Track of the AutoML Conference Vorzeitige Online-Publikation. https://openreview.net/pdf?id=apxqygZeFV
Hasebrook, N., Morsbach, F., Kannengießer, N., Zöller, M., Franke, J., Lindauer, M., Hutter, F., & Sunyaev, A. (2025). Practitioner Motives to Use Different Hyperparameter Optimization Methods. ACM Transactions on Computer-Human Interaction, 32(6), Artikel 59. https://doi.org/10.1145/3745771, https://doi.org/10.48550/arXiv.2203.01717
Henheik, M., Eimer, T., & Lindauer, M. (2025). Revisiting Learning Rate Control. in International Conference on Automated Machine Learning 2025 Vorzeitige Online-Publikation.