Research Lab
My group is interested in Artificial Intelligence, Optimization, and Machine Learning and its applications. 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. Recent examples include the estimation of biomass from satellite data, entanglement and non-locality thresholds via optimization, new constructions in extremal combinatorics via AI, as well as questions around AI and creativity. [group homepage] [more about research and projects]
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 check our openings.
Select Recent Papers
(see publications for a complete list)
- Pelleriti, N., Zimmer, M., Wirth, E., and Pokutta, S. (2025). Approximating Latent Manifolds in Neural Networks via Vanishing Ideals. To Appear in Proceedings of ICML. [arXiv] compalgmltheory
- Mundinger, K., Zimmer, M., Kiem, A., Spiegel, C., and Pokutta, S. (2025). Neural Discovery in Mathematics: Do Machines Dream of Colored Planes? To Appear in Proceedings of ICML. [arXiv] ai4sciencedggraphs (Spotlight + Conference Proceedings)
- Wirth, E., Peña, J., and Pokutta, S. (2025). Fast Convergence of Frank-Wolfe algorithms on polytopes. To Appear in Mathematics of Operations Research. [arXiv] mlopt
- Hendrych, D., Besançon, M., Martínez-Rubio, D., and Pokutta, S. (2025). Secant Line Search for Frank-Wolfe Algorithms. To Appear in Proceedings of ICML. [arXiv] opt
- Roux, C., Martínez-Rubio, D., and Pokutta, S. (2025). Implicit Riemannian Optimism with Applications to Min-Max Problems. To Appear in Proceedings of ICML. [arXiv] mlopt
- Troppens, H., Besançon, M., Wilken, S. E., and Pokutta, S. (2025). Mixed-Integer Optimization for Loopless Flux Distributions in Metabolic Networks. To Appear in Proceedings of Proceedings of Symposium on Experimental Algorithms (SEA) 2025. [arXiv] ai4sciencebiochemistryopt
- Takahashi, S., Pokutta, S., and Takeda, A. (2025). Accelerated Convergence of Frank–Wolfe Algorithms with Adaptive Bregman Step-Size Strategy. Preprint. [arXiv] fwopt
- Haase, J., Hanel, P. H. P., and Pokutta, S. (2025). Has the Creativity of Large-Language Models peaked? An analysis of inter- and intra-LLM variability. Preprint. [arXiv] haiimlsocial
- Zimmer, M., Spiegel, C., and Pokutta, S. (2025). Compression-aware Training of Neural Networks using Frank-Wolfe. In K. Fackeldey, A. Kannan, S. Pokutta, K. Sharma, D. Walter, A. Walther, and M. Weiser (Eds.), Mathematical Optimization for Machine Learning (pp. 137–168). De Gruyter. [PDF] [arXiv] mloptsparsity
- Haase, J., Klessascheck, F., Mendling, J., and Pokutta, S. (2025). Sustainability via LLM Right-sizing. Preprint. [arXiv] haiimlsustainability
- Sharma, U., Goel, K., Dua, A., Pokutta, S., and Woodstock, Z. (2025). A note on asynchronous Projective Splitting in Julia. Preprint. [arXiv] opt
- Aigner, K.-M., Denzler, S., Liers, F., Pokutta, S., and Sharma, K. (2025). Scenario Reduction for Distributionally Robust Optimization. Preprint. [arXiv] optrobopt
- Carderera, A., Pokutta, S., Schütte, C., and Weiser, M. (2025). An efficient first-order conditional gradient algorithm in data-driven sparse identification of nonlinear dynamics to solve sparse recovery problems under noise. To Appear in Journal of Computational and Applied Mathematics. [PDF] [arXiv] [summary] ai4sciencemlopt
- Lasby, M., Zimmer, M., Pokutta, S., and Schultheis, E. (2025). Compressed sparse tiles for memory-efficient unstructured and semi-structured sparsity. Proceedings of ICLR 2025 Workshop on Sparsity in LLMs (SLLM). [PDF] [conference] hpcml
- Głuch, G., Turan, B., Nagarajan, S. G., and Pokutta, S. (2025). The Good, the Bad and the Ugly: Watermarks, Transferable Attacks and Adversarial Defenses. Proceedings of ICLR 2025 Workshop on GenAI Watermarking (WMARK). [arXiv] [summary] [poster] [conference] mlxai
- Fackeldey, K., Kannan, A., Pokutta, S., Sharma, K., Walter, D., Walther, A., and Weiser, M. (Eds.). (2025). Mathematical Optimization for Machine Learning. de Gruyter. mlopt (Proceedings of MATH+ TES Summer Semester 2023)
- Martínez-Rubio, D., and Pokutta, S. (2025). Beyond Short Steps in Frank-Wolfe Algorithms. Preprint. [arXiv] mlopt
- Besançon, M., Designolle, S., Halbey, J., Hendrych, D., Kuzinowicz, D., Pokutta, S., Troppens, H., Viladrich Herrmannsdoerfer, D., and Wirth, E. (2025). Improved algorithms and novel applications of the FrankWolfe.jl library. Preprint. [arXiv] optsoftware
- Sadiku, S., Wagner, M., Nagarajan, S. G., and Pokutta, S. (2025). S-CFE: Simple Counterfactual Explanations. To Appear in Proceedings of AISTATS. [arXiv] mlxai
- Wirth, E., Besançon, M., and Pokutta, S. (2025). The Pivoting Framework: Frank-Wolfe Algorithms with Active Set Size Control. To Appear in Proceedings of AISTATS. [arXiv] mlopt (Oral Presentation + Conference Proceedings)
- Martinez-Rubio, D., Roux, C., Criscitiello, C., and Pokutta, S. (2025). Accelerated Methods for Riemannian Min-Max Problems. To Appear in Proceedings of AISTATS. [arXiv] mlopt
- Mexi, G., Kamp, D., Shinano, Y., Pu, S., Hoen, A., Bestuzheva, K., Hojny, C., Walter, M., Pfetsch, M. E., Pokutta, S., and Koch, T. (2025). State-of-the-art Methods for Pseudo-Boolean Solving with SCIP. Preprint. [arXiv] ipoptsoftware
- Braun, G., Carderera, A., Combettes, C. W., Hassani, H., Karbasi, A., Mokthari, A., and Pokutta, S. (2025). Conditional Gradient Methods. to appear in MOS-SIAM Series on Optimization. [arXiv] mloptsurvey
- Kerdreux, T., d’Aspremont, A., and Pokutta, S. (2025). Local and Global Uniform Convexity Conditions. To Appear in Special Issue of Fields Institute Communications. [arXiv] mlopt
- Haase, J., and Pokutta, S. (2024). Human-AI Co-Creativity: Exploring Synergies Across Levels of Creative Collaboration. Preprint. [arXiv] haiimlsocial
- Designolle, S., Vértesi, T., and Pokutta, S. (2024). Better bounds on Grothendieck constants of finite orders. Preprint. [arXiv] optphysicsquantum
- Abbas, A., Ambainis, A., Augustino, B., Bärtschi, A., Buhrman, H., Coffrin, C., Cortiana, G., Dunjko, V., Egger, D. J., Elmegreen, B. G., Franco, N., Fratini, F., Fuller, B., Gacon, J., Gonciulea, C., Gribling, S., Gupta, S., Hadfield, S., Heese, R., … Zoufal, C. (2024). Quantum Optimization: Potential, Challenges, and the Path Forward. Nature Reviews Physics. [PDF] [arXiv] optphysicsquantumsurvey
Select Recent Talks and Teaching
- 05/2025: (technical) “The Pivoting Framework: Frank-Wolfe Algorithms with Active Set Size Control”. Talk at AISTATS 2025 (Phuket, Thailand). [slides]
- 03/2025: (technical) “The colorful world of Optimization”. Plenary at VIASM Spring School and Workshop on Variational Analysis and Optimization 2025 (Hanoi, Vietnam). [slides]
- 12/2024: (technical) “Exploring Mixed-Integer Convex Optimization with Conditional Gradients: Foundations and Applications”. Talk at MIP International Workshop (Mumbai, India). [slides]
- 12/2024: (technical) “AI x Algorithms x Applications”. Talk at NUS School of Computing Seminar (Singapore).
- 11/2024: (technical) “Extending the Continuum of Six-Colorings”. Talk at MFO Program: Combinatorial Optimization (Oberwolfach, Germany). [slides]
- WS/2024: Discrete Optimization and Machine Learning (seminar)
Recent Blog Posts
- 02/2025: FrankWolfe.jl: An Update on the Julia Package
- 02/2025: Estimating Rare Probabilities
- 11/2024: On the Byzantine-Resilience of Distillation-Based Federated Learning
- 11/2024: The Good, the Bad and the Ugly: Watermarks, Transferable Attacks and Adversarial Defenses
- 10/2024: A short intro to Special Relativity
Select Outreach
- 11/2024: El aprendizaje automático ayuda a atacar problemas matemáticos clásicos (Machine learning helps attack classical mathematical problems). El Pais: Café y teoremas. (Newspaper (Spanish))
- 11/2024: Zukunftsforum KI. IHK Berlin. (Panel Discussion (German))
- 10/2021: Improve the World with Maths?. Humboldt Forum: Discourse, Science and Humanities. (Talk + Discussion (German))
- 05/2021: Durch KI verhandene Ressourcen effizienter nutzen. Aufbruch Ausgabe 28. (Interview (German))
- 12/2020: Folge 7: „Trendsetter Internet? Angstmacher KI? Folgen der Digitalisierung“. Brain City Berlin. (Podcast (German))
News
- 03/2025: Received Science Prize of the Association for Pediatric Orthopedics (VKO) for “Feature Engineering for the Prediction of Scoliosis in 5q-Spinal Muscular Atrophy”, T.-L. Vu-Han (lead author), V. Sunkara, R. Bermudez-Schettino, J. Schwechten, R. Runge, C. Perka, T. Winkler, S. Pokutta, C. Weiß, M. Pumberger.
- 10/2024: Elected Chair of the Cluster of Excellence MATH+ together with Claudia Schillings and Andrea Walther.
- Fall 2024: David Martínez-Rubio started a faculty position at Carlos III University of Madrid. Congratulations!
- Fall 2024: Zev Woodstock started a faculty position at James Madison University. Congratulations!
- 01/2024: The Zuse Institute Berlin (ZIB) is celebrating its 40th anniversary in 2024.