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
- Głuch, G., Turan, B., Nagarajan, S. G., and Pokutta, S. (2024). The Good, the Bad and the Ugly: Watermarks, Transferable Attacks and Adversarial Defenses. Preprint. [arXiv] [poster]
- Sadiku, S., Wagner, M., Nagarajan, S. G., and Pokutta, S. (2024). S-CFE: Simple Counterfactual Explanations. Preprint. [arXiv]
- Designolle, S., Vértesi, T., and Pokutta, S. (2024). Better bounds on Grothendieck constants of finite orders. Preprint. [arXiv]
- 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. To Appear in Nature Reviews Physics. [arXiv]
- Braun, G., Pokutta, S., and Woodstock, Z. (2024). Flexible block-iterative analysis for the Frank-Wolfe algorithm. Preprint. [arXiv]
- Stengl, M., Gelß, P., Klus, S., and Pokutta, S. (2024). Existence and Uniqueness of Solutions of the Koopman–von Neumann Equation on Bounded Domains. To Appear in Journal of Physics A. [arXiv]
- Deza, A., Onn, S., Pokutta, S., and Pournin, L. (2024). Kissing polytopes. To Appear in SIAM Journal on Discrete Mathematics. [PDF] [arXiv]
- Wirth, E., Besançon, M., and Pokutta, S. (2024). The Pivoting Framework: Frank-Wolfe Algorithms with Active Set Size Control. Preprint. [arXiv]
- Wirth, E., Peña, J., and Pokutta, S. (2024). Fast Convergence of Frank-Wolfe algorithms on polytopes. Preprint. [arXiv]
- Martinez-Rubio, D., Roux, C., and Pokutta, S. (2024). Convergence and Trade-Offs in Riemannian Gradient Descent and Riemannian Proximal Point. To Appear in Proceedings of ICML. [arXiv]
- Pauls, J., Zimmer, M., Kelly, U. M., Schwartz, M., Saatchi, S., Ciais, P., Pokutta, S., Brandt, M., and Gieseke, F. (2024). Estimating Canopy Height at Scale. To Appear in Proceedings of ICML. [arXiv] [code]
- Kiem, A., Pokutta, S., and Spiegel, C. (2024). Categorification of Flag Algebras. Proceedings of Discrete Mathematics Days. [arXiv]
- Mundinger, K., Pokutta, S., Spiegel, C., and Zimmer, M. (2024). Extending the Continuum of Six-Colorings. Geombinatorics Quarterly. [arXiv] [summary] [slides]
- Mundinger, K., Zimmer, M., and Pokutta, S. (2024). Neural Parameter Regression for Explicit Representations of PDE Solution Operators. ICLR 2024 Workshop on AI4DifferentialEquations In Science. [PDF] [arXiv] [slides] [poster]
- Designolle, S., Vértesi, T., and Pokutta, S. (2024). Symmetric multipartite Bell inequalities via Frank-Wolfe algorithms. Physical Review A, 109(2). [PDF] [arXiv]
- Roux, C., Zimmer, M., and Pokutta, S. (2024). On the Byzantine-Resilience of Distillation-Based Federated Learning. Preprint. [arXiv] [code]
- Pokutta, S. (2024). The Frank-Wolfe algorithm: a short introduction. Jahresbericht Der Deutschen Mathematiker-Vereinigung, 126, 3–35. [PDF] [arXiv]
- Zimmer, M., Spiegel, C., and Pokutta, S. (2024). Sparse Model Soups: A Recipe for Improved Pruning via Model Averaging. To Appear in Proceedings of ICLR. [arXiv]
- 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
- 07/2024: (technical) “German <-> Japanese Supercomputing - a success story”. Keynote at 16th JHPCN symposium (Tokyo, Japan). [slides]
- 07/2024: (technical) “Extending the Continuum of Six-Colorings”. Talk at Conference on Discrete Optimization and Machine Learning (Tokyo, Japan). [slides]
- 06/2024: (general) “Cargo-Kult trifft auf große Sprachmodelle: Entmystifizierung von KI?”. Talk at Lange Nacht der Wissenschaften (Berlin, Germany).
- 03/2024: (general) “The Cargo Cult Meets Large Language Models: Demystifying AI Sentiments?”. Talk at Hong Kong Analytics Community Meeting (Hong Kong, China).
- 03/2024: (technical) “Alternating Linear Minimization: Revisiting von Neumann’s alternating projections”. Talk at CUHK-Shenzhen Seminar (Shenzhen, China). [slides]
- WS/2024: Discrete Optimization and Machine Learning (seminar)
Recent Blog Posts
- 10/2024: A short intro to Special Relativity
- 09/2024: A Secant Method Line Search for Frank-Wolfe algorithms
- 07/2024: Extending the Continuum of Six-Colorings
- 01/2024: ZIB’s Anniversary: Celebrating 40 Years of Innovation in Mathematics and Computer Science
- 08/2023: Accelerated and Sparse Algorithms for Approximate Personalized PageRank and Beyond
Select Outreach
- 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))
- 09/2019: Drei Fragen an Sebastian Pokutta. Felix-Klein-Herbstworkshop »Discrete Optimization«. (Interview (German))
News
- 01/2024: The Zuse Institute Berlin (ZIB) is celebrating its 40th anniversary in 2024.
- 05/2023: Received Gödel Prize together with Samuel Fiorini, Serge Massar, Hans Raj Tiwary, Ronald de Wolf, and Thomas Rothvoss.
- 05/2023: We are organizing the fifth conference on “Discrete Optimization and Machine Learning” in Aug 2023 at GRIPS in Tokyo.
- 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]