Sebastian Pokutta

Sebastian Pokutta

Artificial Intelligence, Optimization, and Machine Learning. Professor @TUBerlin, Vice President @ZuseInstitute



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.

Recent Papers.

  1. Pokutta, S., Spiegel, C., and Zimmer, M. (2020). Deep Neural Network Training with Frank-Wolfe. Preprint. [arXiv] [summary] [code]
  2. Combettes, C. W., Spiegel, C., and Pokutta, S. (2020). Projection-Free Adaptive Gradients for Large-Scale Optimization. Preprint. [arXiv] [summary] [code]
  3. Sofranac, B., Gleixner, A., and Pokutta, S. (2020). Accelerating Domain Propagation: an Efficient GPU-Parallel Algorithm over Sparse Matrices. To Appear in Proceedings of IA^3 at SC20. [arXiv] [summary] [slides]
  4. Pokutta, S. (2020). Restarting Algorithms: Sometimes there is Free Lunch. To Appear in Proceedings of CPAIOR. [arXiv] [slides] [video]
  5. Mortagy, H., Gupta, S., and Pokutta, S. (2020). Walking in the Shadow: A New Perspective on Descent Directions for Constrained Minimization. To Appear in Proceedings of NeurIPS. [arXiv] [slides] [poster] [code]
  6. Kerdreux, T., d’Aspremont, A., and Pokutta, S. (2020). Projection-Free Optimization on Uniformly Convex Sets. Preprint. [arXiv] [summary]
  7. Combettes, C. W., and Pokutta, S. (2020). Boosting Frank-Wolfe by Chasing Gradients. To Appear in Proceedings of ICML. [arXiv] [summary] [slides] [code] [video]
  8. Carderera, A., and Pokutta, S. (2020). Second-order Conditional Gradient Sliding. Preprint. [arXiv] [summary] [code]
  9. Pfetsch, M., and Pokutta, S. (2020). IPBoost – Non-Convex Boosting via Integer Programming. To Appear in Proceedings of ICML. [arXiv] [summary] [slides] [code]
  10. Pokutta, S., Singh, M., and Torrico, A. (2020). On the Unreasonable Effectiveness of the Greedy Algorithm: Greedy Adapts to Sharpness. To Appear in Proceedings of ICML. [arXiv] [summary] [slides] [poster] [video]

Select Recent Talks and Teaching.

Recent Blog Posts.

News.