Prof. Dr. Sebastian Pokutta
Vice President and Division Head
Mathematical Algorithmic Intelligence
AI in Society, Science, and Technology (AIS²T)
Zuse Institute Berlin (ZIB)
Professor for
Optimization and Machine Learning
Institute of Mathematics
Electrical Engineering and Computer Science (courtesy)
Technische Universität Berlin
Research Lab. My group is interested in Artificial Intelligence, Optimization, and Machine Learning. We develop new methodologies (e.g., new optimization and learning algorithms), work on combining learning and decision-making, as well as design AI Systems for real-world deployment in various application contexts. [more]
(Informal) TL;DR. We use computers to learn from data and make better decisions.
Prospective Students. If you are interested in working in our group or writing your MS/BS thesis please only use the email applications-aisst@zib.de.
Recent Papers.
- Parczyk, O., Pokutta, S., Spiegel, C., and Szabó, T. (2022). Fully Computer-Assisted Proofs in Extremal Combinatorics. To Appear in Proceedings of AAAI. [arXiv] [slides]
- Martinez-Rubio, D., and Pokutta, S. (2022). Accelerated Riemannian Optimization: Handling Constraints to Bound Geometric Penalties. To Appear in NeurIPS OPT 2022 Workshop. [poster]
- Criado, F., Martinez-Rubio, D., and Pokutta, S. (2022). Fast Algorithms for Packing Proportional Fairness and its Dual. To Appear in Proceedings of NeurIPS. [arXiv] [poster]
- Braun, G., Carderera, A., Combettes, C. W., Hassani, H., Karbasi, A., Mokthari, A., and Pokutta, S. (2022). Conditional Gradient Methods. Preprint.
- Hendrych, D., Troppens, H., Besançon, M., and Pokutta, S. (2022). Convex integer optimization with Frank-Wolfe methods. Preprint. [arXiv] [slides] [code]
- Wirth, E., Kera, H., and Pokutta, S. (2022). Approximate Vanishing Ideal Computations at Scale. Preprint. [arXiv] [slides]
- Parczyk, O., Pokutta, S., Spiegel, C., and Szabó, T. (2022). New Ramsey Multiplicity Bounds and Search Heuristics. Preprint. [arXiv] [slides]
- Wäldchen, S., Sharma, K., Zimmer, M., and Pokutta, S. (2022). Merlin-Arthur Classifiers: Formal Interpretability with Interactive Black Boxes. Preprint. [arXiv]
- Macdonald, J., Besançon, M., and Pokutta, S. (2022). Interpretable Neural Networks with Frank-Wolfe: Sparse Relevance Maps and Relevance Orderings. To Appear in Proceedings of ICML. [arXiv] [poster] [video]
- Tsuji, K., Tanaka, K., and Pokutta, S. (2022). Pairwise Conditional Gradients without Swap Steps and Sparser Kernel Herding. To Appear in Proceedings of ICML. [arXiv] [summary] [slides] [code] [video]
- Zimmer, M., Spiegel, C., and Pokutta, S. (2022). Compression-aware Training of Neural Networks using Frank-Wolfe. Preprint. [arXiv]
- Gelß, P., Klus, S., Shakibaei, Z., and Pokutta, S. (2022). Low-rank tensor decompositions of quantum circuits. Preprint. [arXiv]
- Deza, A., Pokutta, S., and Pournin, L. (2022). The complexity of geometric scaling. Preprint. [arXiv]
- Wäldchen, S., Huber, F., and Pokutta, S. (2022). Training Characteristic Functions with Reinforcement Learning: XAI-methods play Connect Four. To Appear in Proceedings of ICML. [arXiv] [poster] [video]
- Gasse, M., Cappart, Q., Charfreitag, J., Charlin, L., Chételat, D., Chmiela, A., Dumouchelle, J., Gleixner, A., Kazachkov, A. M., Khalil, E., Lichocki, P., Lodi, A., Lubin, M., Maddison, C. J., Morris, C., Papageorgiou, D. J., Parjadis, A., Pokutta, S., Prouvost, A., … Kun, M. (2022). The Machine Learning for Combinatorial Optimization Competition (ML4CO): Results and Insights. Preprint. [arXiv]
- Hunkenschröder, C., Pokutta, S., and Weismantel, R. (2022). Optimizing a low-dimensional convex function over a high-dimensional cube. To Appear in SIAM Journal on Optimization. [arXiv]
- Kossen, T., Hirzel, M. A., Madai, V. I., Boenisch, F., Hennemuth, A., Hildebrand, K., Pokutta, S., Sharma, K., Hilbert, A., Sobesky, J., Galinovic, I., Khalil, A. A., Fiebach, J. B., and Frey, D. (2022). Towards sharing brain images: Differentially private TOF-MRA images with segmentation labels using generative adversarial networks. Frontiers in Artificial Intelligence. [PDF]
- Kerdreux, T., Scieur, D., d’Aspremont, A., and Pokutta, S. (2022). Strong Convexity of Feasible Sets in Riemannian Manifolds. Preprint.
- Wirth, E., Kerdreux, T., and Pokutta, S. (2022). Acceleration of Frank-Wolfe algorithms with open loop step-sizes. Preprint. [arXiv]
- Wirth, E., and Pokutta, S. (2022). Conditional Gradients for the Approximately Vanishing Ideal. To Appear in Proceedings of AISTATS. [arXiv] [summary] [poster] [code]
- Roux, C., Wirth, E., Pokutta, S., and Kerdreux, T. (2021). Efficient Online-Bandit Strategies for Minimax Learning Problems. Preprint. [arXiv]
- Kerdreux, T., d’Aspremont, A., and Pokutta, S. (2021). Local and Global Uniform Convexity Conditions. Preprint. [arXiv]
- Braun, G., and Pokutta, S. (2021). Dual Prices for Frank-Wolfe Algorithms. Preprint. [arXiv]
Select Recent Talks and Teaching.
- 09/2022: (technical) “Convex integer optimization with Frank-Wolfe methods”. Talk at Advances in Classical and Quantum Algorithms for Optimization and Machine Learning (Tokyo, Japan). [slides]
- 07/2022: (technical) “Structured ML Training via Conditional Gradients”. Plenary at Workshop on Algorithmic Optimization and Data Science (Trier, Germany). [slides]
- 04/2022: (technical) “Conditional Gradients in Machine Learning and Optimization”. Talk at IST ELLIS Seminar Series (Klosterneuburg, Austria). [slides]
- 11/2021: (technical) “Discrete Optimization in Machine Learning - an (informal) overview”. Talk at Oberwolfach Workshop on Combinatorial Optimization (Oberwolfach, Germany). [slides]
- 10/2021: (technical) “Fast algorithms for 1-fair packing (and its dual)”. Talk at HIM Workshop: Continuous approaches to discrete optimization (Bonn, Germany). [slides]
- SoSe/2021: Discrete Optimization and Machine Learning (seminar)
Recent Blog Posts.
- 08/2022: Boscia.jl - a new Mixed-Integer Convex Programming (MICP) solver
- 07/2022: Acceleration of Frank-Wolfe algorithms with open loop step-sizes
- 05/2022: Pairwise Conditional Gradients without Swap Steps
- 05/2022: Quantum Computing for the Uninitiated: The Basics
- 02/2022: Conditional Gradients for the Approximately Vanishing Ideal
News.
- 06/2022: Symposium on Theory of Computing (STOC) Test of Time award (10 years) for “Linear vs. Semidefinite Extended Formulations: Exponential Separation and Strong Lower Bounds”, S. Fiorini, S. Massar, S. Pokutta, H.R. Tiwary, R. de Wolf from 2012.
- 06/2022: 6th RIKEN-IMI-ISM-ZIB-MODAL-NHR Workshop on Advances in Classical and Quantum Algorithms for Optimization and Machine Learning in Japan. [link]
- 06/2022: New ZIB videos available. [youtube channel]. (german only)
- 06/2022: Interview on using AI to combat and mitigate climate change (German) [article] [magazine]
- 10/2021: Math+ Cluster presentation at the Humboldt Forum “Mit Mathematik die Welt verbessern?” (German) [video]