Prof. Dr. Sebastian Pokutta
Vice President
Zuse Institute Berlin (ZIB)
Professor for
Optimization and Machine Learning
Mathematics and EECS (courtesy)
Technische Universität Berlin
Vice President
Zuse Institute Berlin (ZIB)
Professor for
Optimization and Machine Learning
Mathematics and EECS (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.
- Thuerck, D., Sofranac, B., Pfetsch, M., and Pokutta, S. (2023). Learning Cuts via Enumeration Oracles. Preprint. [arXiv]
- Martinez-Rubio, D., Wirth, E., and Pokutta, S. (2023). Accelerated and Sparse Algorithms for Approximate Personalized PageRank and Beyond. To Appear in Proceedings of COLT. [arXiv]
- Martinez-Rubio, D., and Pokutta, S. (2023). Accelerated Riemannian Optimization: Handling Constraints to Bound Geometric Penalties. To Appear in Proceedings of COLT. [arXiv] [poster]
- Aigner, K., Bärmann, A., Braun, K., Liers, F., Pokutta, S., Schneider, O., Sharma, K., and Tschuppik, S. (2023). Data-driven Distributionally Robust Optimization over Time. To Appear in INFORMS Journal on Optimization. [arXiv]
- Kreimeier, T., Pokutta, S., Walther, A., and Woodstock, Z. (2023). On a Frank-Wolfe Approach for Abs-smooth Functions. Preprint. [arXiv]
- Designolle, S., Iommazzo, G., Besançon, M., Knebel, S., Gelß, P., and Pokutta, S. (2023). Improved local models and new Bell inequalities via Frank-Wolfe algorithms. Preprint. [arXiv]
- Zimmer, M., Spiegel, C., and Pokutta, S. (2023). How I Learned to Stop Worrying and Love Retraining. To Appear in Proceedings of ICLR. [arXiv] [code]
- Chmiela, A., Gleixner, A., Lichocki, P., and Pokutta, S. (2023). Online Learning for Scheduling MIP Heuristics. To Appear in Proceedings of CPAIOR.
- Wirth, E., Kera, H., and Pokutta, S. (2023). Approximate Vanishing Ideal Computations at Scale. To Appear in Proceedings of ICLR. [arXiv] [slides]
- Wirth, E., Kerdreux, T., and Pokutta, S. (2023). Acceleration of Frank-Wolfe algorithms with open loop step-sizes. To Appear in Proceedings of AISTATS. [arXiv]
- Braun, G., Pokutta, S., and Weismantel, R. (2022). Alternating Linear Minimization: Revisiting von Neumann’s alternating projections. Preprint. [arXiv] [slides] [video]
- 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]
- Braun, G., Carderera, A., Combettes, C. W., Hassani, H., Karbasi, A., Mokthari, A., and Pokutta, S. (2022). Conditional Gradient Methods. Preprint. [arXiv]
Select Recent Talks and Teaching.
- 05/2023: (technical) “Alternating Linear Minimization: Revisiting von Neumann’s alternating projections”. Talk at University of Magdeburg MathCoRe Lecture (Magdeburg, Germany). [slides]
- 04/2023: (technical) “Conditional Gradients in Machine Learning”. Talk at Yale Statistics and Data Science Seminar Series (New Haven, CT). [slides]
- 03/2023: (technical) “Alternating Linear Minimization: Revisiting von Neumann’s alternating projections”. Talk at ICERM Workshop: Combinatorics and Optimization (Providence, RI). [slides] [video]
- 03/2023: (technical) “Structured ML Training via Conditional Gradients”. Talk at Columbia IEOR Seminar Series (New York, NY). [slides]
- 03/2023: (technical) “Conditional Gradients – an overview”. Keynote at 2nd Vienna Workshop on Computational Optimization (Vienna, Austria). [slides]
- WS/2022: Discrete Optimization and Machine Learning (seminar)
Recent Blog Posts.
- 05/2023: Improved local models and new Bell inequalities via Frank-Wolfe algorithms
- 12/2022: Sh**t you can do with the euclidean norm
- 11/2022: Monograph on Conditional Gradients and Frank-Wolfe methods
- 08/2022: Boscia.jl - a new Mixed-Integer Convex Programming (MICP) solver
- 07/2022: Acceleration of Frank-Wolfe algorithms with open loop step-sizes
News.
- 05/2023: Received Gödel Prize together with Samuel Fiorini, Serge Massar, Hans Raj Tiwary, Ronald de Wolf, and Thomas Rothvoss
- 02/2023: We are organizing a Thematic Einstein Semester on “Mathematical Optimization for Machine Learning” within the Math+ Cluster of Excellence. The semester consists of various activities throughout the semester with three workshops, a conference, and a summer school as some of the highlights. We are looking forward to seeing you in Berlin!
- 11/2022: We finished our monograph on Frank-Wolfe methods a.k.a. Conditional Gradients. [arxiv] [webpage] [blog]
- 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]