Sebastian Pokutta

Artificial Intelligence, Optimization, and Machine Learning. Professor @TUBerlin, Vice President @ZuseInstitute, Chair @MATH+, Chair @MODAL

Filter by tags:

In Preparation / Articles Pending Review ⏵

  1. Tadinada, S. H., Pokutta, S., and Walther, A. (2026). Abs-Smooth Frank-Wolfe Method: Primal-Dual Analysis, Heavy Ball Momentum, and Inexact Oracles. Preprint. [arXiv] fwopt
  2. Pelleriti, N., Nelaturu, S. H., Zhou, Z., Li, Z., Zimmer, M., Han, B., and Pokutta, S. (2026). What Do Evolutionary Coding Agents Evolve? Preprint. [arXiv] agenticllmmlneuro-compute
  3. Tjusila, G. K., Hoen, A., Kempke, N.-C., Mexi, G., Berthold, T., Gleixner, A., Koch, T., and Pokutta, S. (2026). CHAP: A Hybrid GPU-CPU Heuristic for MIP. Preprint. [arXiv] gpumip
  4. Berthold, T., Kamp, D., Mexi, G., Pokutta, S., and Pólik, I. (2026). Out-of-the-Box Global Optimization for Packing Problems: New Models and Improved Solutions. Preprint. [arXiv] computationalllmnlpoptpacking
  5. Poirion, P.-L., Pokutta, S., and Takeda, A. (2026). Random-Subspace Frank–Wolfe over Strongly Convex Sets. Preprint. [arXiv] fwopt
  6. Halbey, J., Roux, C., and Pokutta, S. (2026). Curvature-Dependent Lower Bounds for Frank-Wolfe. Preprint. [arXiv] complexityfwlowerboundsopt
  7. Xu, L., Zhou, Y., and Pokutta, S. (2026). Agentic MIP Research: Accelerated Constraint Handler Generation. Preprint. [arXiv] agenticcomputationalllmmipopt
  8. Gonnermann-Müller, J., Haase, J., Leins, N., Kosch, T., and Pokutta, S. (2026). LLM-Based Educational Simulation: Evaluating Temporal Student Persona Stability Across ADHD Profiles. Preprint. [arXiv] haiillmmlmultiagentsocial
  9. Geiselmann, Z., Joswig, M., Kastner, L., Mundinger, K., Pokutta, S., Spiegel, C., Wack, M., and Zimmer, M. (2026). Fast Isotopy Computation for T-Curves. Preprint. [arXiv] ai4mathalggeomcombinatoricscompalg
  10. Pokutta, S. (2026). Frank-Wolfe Beyond 1/t Convergence. Preprint. [arXiv] complexityfwopt
  11. Zimmer, M., Pelleriti, N., Roux, C., and Pokutta, S. (2026). The Agentic Researcher: A Practical Guide to AI-Assisted Research in Mathematics and Machine Learning. Preprint. [arXiv] [summary] [code] agenticai4mathml
  12. Pauls, J., Schrödter, K., Ligensa, S., Schwartz, M., Turan, B., Zimmer, M., Saatchi, S., Pokutta, S., Ciais, P., and Gieseke, F. (2026). ECHOSAT: Estimating Canopy Height Over Space And Time. Preprint. [arXiv] [code] [visuals] ai4sciencemlsustainability
  13. Khoruzhii, K., Gelß, P., and Pokutta, S. (2026). Tensor Decomposition for Non-Clifford Gate Minimization. Preprint. [arXiv] compalgquantum
  14. Geiselmann, Z., Joswig, M., Kastner, L., Mundinger, K., Pokutta, S., Spiegel, C., Wack, M., and Zimmer, M. (2026). Patchworked Curves of Degree Seven. Preprint. [arXiv] ai4mathalggeomcombinatoricscompalg
  15. Leins, N., Gonnermann-Müller, J., Teichmann, M., and Pokutta, S. (2026). Investigating the Influence of Spatial Ability in Augmented Reality-assisted Robot Programming. Preprint. [arXiv] arhrimlrobotics
  16. Gonnermann-Müller, J., Haase, J., Leins, N., Kosch, T., and Pokutta, S. (2026). Stable Personas: Dual-Assessment of Temporal Stability in LLM-Based Human Simulation. Preprint. [arXiv] haiillmmlmultiagentsocial
  17. Haase, J., and Pokutta, S. (2026). The Hidden Cost of Tokenization: Why (most) Non-English Speakers Pay More for Less. Preprint. [arXiv] [summary] fairnessllmmlmultilingual
  18. Haase, J., Gonnermann-Müller, J., and Pokutta, S. (2026). Building Socially Grounded Multi-Agent LLM Systems Requires the Transition from Static LLM Prompting to Autonomous Multi-Agent Ecosystems. Preprint. [arXiv] haiillmmlmultiagentsocial
  19. Haase, J., Gonnermann-Müller, J., Hanel, P. H. P., Leins, N., Kosch, T., Mendling, J., and Pokutta, S. (2026). Within-Model vs Between-Prompt Variability in Large Language Models for Creative Tasks. Preprint. [arXiv] creativityhaiillmml
  20. Zimmer, M., Roux, C., Wagner, M., Hendrych, D., and Pokutta, S. (2025). SparseSwaps: Tractable LLM Pruning Mask Refinement at Scale. Preprint. [arXiv] llmmlpruningsparsity
  21. Kuzinowicz, D., Lichocki, P., Mexi, G., Pfetsch, M. E., Pokutta, S., and Zimmer, M. (2025). Objective Coefficient Rounding and Almost Symmetries in Binary Programs. Preprint. [arXiv] computationalmipoptsymmetry
  22. Xu, L., Liu, Y.-C., and Pokutta, S. (2025). Convex semidefinite tensor optimization and quantum entanglement. Preprint. [arXiv] optquantum
  23. Hojny, C., Besançon, M., Bestuzheva, K., Borst, S., Chmiela, A., Dionísio, J., Eifler, L., Ghannam, M., Gleixner, A., Göß, A., Hoen, A., van der Hulst, R., Kamp, D., Koch, T., Kofler, K., Lentz, J., Maher, S. J., Mexi, G., Mühmer, E., … Xu, L. (2025). The SCIP Optimization Suite 10.0. Preprint. [arXiv] computationalipoptsoftware
  24. Xiao, W., Hendrych, D., Besançon, M., and Pokutta, S. (2025). Boscia.jl: A review and tutorial. Preprint. [arXiv] fwminlpoptsoftware
  25. Wagner, M., Roux, C., Zimmer, M., and Pokutta, S. (2025). A Free Lunch in LLM Compression: Revisiting Retraining after Pruning. Preprint. [arXiv] llmmlpruningsparsity
  26. Roux, C., Zimmer, M., d’Aspremont, A., and Pokutta, S. (2025). Don’t Be Greedy, Just Relax! Pruning LLMs via Frank-Wolfe. Preprint. [arXiv] fwllmmloptpruningsparsity
  27. Gonnermann-Müller, J., Haase, J., Fackeldey, K., and Pokutta, S. (2025). FACET: Teacher-Centred LLM-Based Multi-Agent Systems – Towards Personalized Educational Worksheets. Preprint. [arXiv] educationhaiillmmlmultiagent
  28. Mexi, G., Hendrych, D., Designolle, S., Besançon, M., and Pokutta, S. (2025). A Frank-Wolfe-based primal heuristic for quadratic mixed-integer optimization. Preprint. [arXiv] ipminlpoptsoftware
  29. Pokutta, S. (2025). Scalable DC Optimization via Adaptive Frank-Wolfe Algorithms. Preprint. [arXiv] computationalopt
  30. Liu, Y.-C., Halbey, J., Pokutta, S., and Designolle, S. (2025). A Unified Toolbox for Multipartite Entanglement Certification. Preprint. [arXiv] optphysicsquantum
  31. Porto, L. E. A., Designolle, S., Pokutta, S., and Quintino, M. T. (2025). Measurement incompatibility and quantum steering via linear programming. Preprint. [arXiv] optphysicsquantum
  32. Haase, J., and Pokutta, S. (2025). Beyond Static Responses: Multi-Agent LLM Systems as a New Paradigm for Social Science Research. Preprint. [arXiv] haiimlsocial
  33. Sadiku, S., Chitranshi, K., Kera, H., and Pokutta, S. (2025). Training on Plausible Counterfactuals Removes Spurious Correlations. Preprint. [arXiv] mlxai
  34. Wirth, E., Peña, J., and Pokutta, S. (2025). Adaptive Open-Loop Step-Sizes for Accelerated Convergence Rates of the Frank-Wolfe Algorithm. Preprint. [arXiv] complexityfwopt
  35. Sharma, U., Goel, K., Dua, A., Pokutta, S., and Woodstock, Z. (2025). A note on asynchronous Projective Splitting in Julia. Preprint. [arXiv] opt
  36. Aigner, K.-M., Denzler, S., Liers, F., Pokutta, S., and Sharma, K. (2025). Scenario Reduction for Distributionally Robust Optimization. Preprint. [arXiv] optrobopt
  37. 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] computationalipoptsoftware
  38. Braun, G., Pokutta, S., and Woodstock, Z. (2024). Flexible block-iterative analysis for the Frank-Wolfe algorithm. Preprint. [arXiv] mlopt
  39. Sharma, K., Hendrych, D., Besançon, M., and Pokutta, S. (2024). Network Design for the Traffic Assignment Problem with Mixed-Integer Frank-Wolfe. Preprint. [arXiv] [code] ipopt
  40. Zimmer, M., Andoni, M., Spiegel, C., and Pokutta, S. (2023). PERP: Rethinking the Prune-Retrain Paradigm in the Era of LLMs. Preprint. [arXiv] [code] llmmlpruningsparsity
  41. Braun, G., Pokutta, S., and Weismantel, R. (2022). Alternating Linear Minimization: Revisiting von Neumann’s alternating projections. Preprint. [arXiv] [slides] [video] opt
  42. Gelß, P., Klus, S., Shakibaei, Z., and Pokutta, S. (2022). Low-rank tensor decompositions of quantum circuits. Preprint. [arXiv] quantum
  43. Pokutta, S., Spiegel, C., and Zimmer, M. (2020). Deep Neural Network Training with Frank-Wolfe. Preprint. [arXiv] [summary] [code] mloptsparsity
  44. Combettes, C. W., Spiegel, C., and Pokutta, S. (2020). Projection-Free Adaptive Gradients for Large-Scale Optimization. Preprint. [arXiv] [summary] [code] mlopt
  45. Bärmann, A., Martin, A., Pokutta, S., and Schneider, O. (2018). An Online-Learning Approach to Inverse Optimization. Submitted. [arXiv] [summary] [slides] ipmlopt

Books and Edited Volumes ⏵

  1. Bülte, C., Burger, M., Hein, M., Kutyniok, G., Pokutta, S., and Steinwart, I. (Eds.). (2026). Theoretical Foundations of Deep Learning (p. 766). Springer. ml
  2. Dang, S., Deza, A., Gupta, S., McNicholas, P. D., Pokutta, S., and Sugiyama, M. (Eds.). (2026). Data Science and Optimization (Vol. 91). Springer. mlopt
  3. Fackeldey, K., Kannan, A., Pokutta, S., Sharma, K., Walter, D., Walther, A., and Weiser, M. (Eds.). (2025). Mathematical Optimization for Machine Learning. de Gruyter. [PDF] mlopt (Proceedings of MATH+ TES Summer Semester 2023)
  4. Braun, G., Carderera, A., Combettes, C. W., Hassani, H., Karbasi, A., Mokthari, A., and Pokutta, S. (2025). Conditional Gradient Methods. MOS-SIAM Series on Optimization. [PDF] [arXiv] mloptsurvey

Refereed Conference Proceedings ⏵

  1. Zimmer, M., Pelleriti, N., Roux, C., and Pokutta, S. (2026). The Agentic Researcher: A Practical Guide to AI-Assisted Research in Mathematics and Machine Learning. Proceedings of the ICML 2026 Workshop on AI as a Tool for Mathematics, Computer Science, and Machine Learning (AI4Research). [PDF] [arXiv] [summary] [code] agenticai4mathml (Oral Presentation + Workshop)
  2. Zhou, Z., Li, Z., Huang, W., Li, X., Cao, C., Feng, X., Lu, X., Hu, J., Lu, M., Xie, Y., Pelleriti, N., Liu, S., Zimmer, M., Miranda, B., Yao, J., Liu, B., Koyejo, S., Pokutta, S., and Han, B. (2026). Reasoning Is More Than the Model: Harness-Aware Evaluation of Agents on Verifiable Reasoning Tasks. Proceedings of the ICML 2026 Workshop on AI as a Tool for Mathematics, Computer Science, and Machine Learning (AI4Research). agenticevaluationllmml
  3. Haase, J., and Pokutta, S. (2026). Structured Creativity Methods for Multi-Agent LLMs: Brainwriting Outperforms Disney and Double Diamond. Proceedings of ICML 2026 Workshop on Human-AI Co-Creativity (GenAICreativity). creativityllmmlmulti-agent
  4. Muhtar, D., Song, X., Pokutta, S., Zimmer, M., Pelleriti, N., Hofmann, T., and Liu, S. (2026). When Does Sparsity Mitigate the Curse of Depth in LLMs. Proceedings of the 43rd International Conference on Machine Learning (ICML). [arXiv] [code] llmmlsparsity
  5. Halbey, J., Deza, D., Zimmer, M., Roux, C., Stellato, B., and Pokutta, S. (2026). Lower Bounds for Frank-Wolfe on Strongly Convex Sets. Proceedings of the 43rd International Conference on Machine Learning (ICML). [arXiv] [summary] complexityfwlowerboundsopt
  6. Schiekiera, L., Zimmer, M., Roux, C., Pokutta, S., and Günther, F. (2026). From Associations to Activations: Comparing Behavioral and Hidden-State Semantic Geometry in LLMs. Proceedings of the 43rd International Conference on Machine Learning (ICML). [arXiv] [summary] cognitivellmmlxai
  7. Turan, B., Asadulla, S., Steinmann, D., Kersting, K., Stammer, W., and Pokutta, S. (2026). Neural Concept Verifier: Scaling Prover-Verifier Games via Concept Encodings. Proceedings of the 43rd International Conference on Machine Learning (ICML). [arXiv] mlxai (Spotlight + Conference Proceedings)
  8. Haase, J., and Pokutta, S. (2026). The Missing Drive: Functional Analogs of Intrinsic Motivation in Large Language Models for Creative Tasks. Proceedings of ICML 2026 Workshop on Human-AI Co-Creativity (GenAICreativity). creativityllmml
  9. Gonnermann-Müller, J., Haase, J., Leins, N., Kosch, T., and Pokutta, S. (2026). Maintaining Stable Personas? Examining Temporal Stability in LLM-Based Human Simulation. Proceedings of the ACM CHI Conference on Human Factors in Computing Systems (CHI). haiillmmlmultiagentsocial
  10. Haase, J., Gonnermann-Müller, J., Hanel, P. H. P., Leins, N., Kosch, T., Mendling, J., and Pokutta, S. (2026). It’s Not Just the Prompt: Model Choice Dominates LLM Creative Output. Proceedings of the ACM CHI Conference on Human Factors in Computing Systems (CHI). creativityhaiillmml
  11. Khoruzhii, K., Gelß, P., and Pokutta, S. (2026). Faster Algorithms for Structured Matrix Multiplication via Flip Graph Search. Proceedings of the International Symposium on Symbolic and Algebraic Computation (ISSAC). [arXiv] compalgcomputational
  12. Muhtar, D., Song, X., Pokutta, S., Zimmer, M., Pelleriti, N., Hofmann, T., and Liu, S. (2026). When Does Sparsity Mitigate the Curse of Depth in LLMs. Proceedings of ICLR 2026 Workshop on Decoding LLM Training and Adaptation (DeLTa). [PDF] [arXiv] [code] llmmlsparsity
  13. Tadinada, S. H., Siebert, T., Fuhrmann, J., Pokutta, S., and Walther, A. (2026). An AD-enabled Frank-Wolfe Method for Non-smooth Optimization. In Proceedings of the 2024 International Conference on Algorithmic Differentiation (AD) (pp. 90–106). SIAM. [PDF] opt
  14. Berthold, T., Kamp, D., Mexi, G., Pokutta, S., and Pólik, I. (2026). Global Optimization for Combinatorial Geometry Problems Revisited in the Era of LLMs. To Appear in Proceedings of ISCO, Lecture Notes in Computer Science. [arXiv] computationalllmnlpopt
  15. Xiao, W., Besançon, M., Gelß, P., Hendrych, D., Klus, S., and Pokutta, S. (2026). Graph Isomorphism: Mixed-Integer Convex Optimization from First-Order Methods. To Appear in Proceedings of CPAIOR. [arXiv] computationalgraphsmipopt
  16. Martínez-Rubio, D., and Pokutta, S. (2026). Beyond Short Steps in Frank-Wolfe Algorithms. To Appear in Proceedings of the International Conference on Learning Representations (ICLR). [arXiv] mlopt
  17. Leins, N., Gonnermann-Müller, J., Teichmann, M., and Pokutta, S. (2026). Beyond Static Instruction: A Multi-Agent AI Framework for Adaptive Augmented Reality Robot Training. Companion Proceedings of the 21st ACM/IEEE International Conference on Human-Robot Interaction (HRI), 989–993. [PDF] [arXiv] arhrimlrobotics
  18. Pelleriti, N., Spiegel, C., Liu, S., Martínez-Rubio, D., Zimmer, M., and Pokutta, S. (2026). Neural Sum-of-Squares: Certifying the Nonnegativity of Polynomials with Transformers. To Appear in Proceedings of the International Conference on Learning Representations (ICLR). [arXiv] ai4mathcompalgml
  19. Iommazzo, G., Martínez-Rubio, D., Criado, F., Wirth, E., and Pokutta, S. (2026). Linear Convergence of the Frank-Wolfe Algorithm over Product Polytopes. To Appear in Proceedings of AISTATS. [arXiv] mlopt
  20. Urbano, A., Romero, D. W., Zimmer, M., and Pokutta, S. (2026). RECON: Robust symmetry discovery via Explicit Canonical Orientation Normalization. To Appear in Proceedings of the International Conference on Learning Representations (ICLR). [arXiv] mlsymmetry
  21. Takahashi, S., Pokutta, S., and Takeda, A. (2026). Fast Frank–Wolfe Algorithms with Adaptive Bregman Step-Size for Weakly Convex Functions. To Appear in Proceedings of the International Conference on Learning Representations (ICLR). [arXiv] complexityfwopt
  22. Kerdreux, T., Scieur, D., Martinez-Rubio, D., d’Aspremont, A., and Pokutta, S. (2026). Strong Convexity of Sets in Riemannian Manifolds. To Appear in Proceedings of the International Conference on Learning Representations (ICLR). [arXiv] mlopt
  23. Gonnermann-Müller, J., Haase, J., Leins, N., Igel, M., Fackeldey, K., and Pokutta, S. (2026). FACET: Multi-Agent AI Supporting Teachers in Scaling Differentiated Learning for Diverse Students. Proceedings of the 35th International Joint Conference on Artificial Intelligence (IJCAI). [arXiv] educationhaiillmmlmultiagent
  24. Halbey, J., Rakotomandimby, S., Besançon, M., Designolle, S., and Pokutta, S. (2025). Efficient Quadratic Corrections for Frank-Wolfe Algorithms. Advances in Neural Information Processing Systems (NeurIPS), 38. [arXiv] fwopt
  25. Kera, H., Pelleriti, N., Ishihara, Y., Zimmer, M., and Pokutta, S. (2025). Computational Algebra with Attention: Transformer Oracles for Border Basis Algorithms. Advances in Neural Information Processing Systems (NeurIPS), 38. [arXiv] ai4mathcompalgml
  26. Głuch, G., Turan, B., Nagarajan, S. G., and Pokutta, S. (2025). The Good, the Bad and the Ugly: Watermarks, Transferable Attacks and Adversarial Defenses. Advances in Neural Information Processing Systems (NeurIPS), 38. [PDF] [arXiv] [summary] [poster] mlxai
  27. Haase, J., Hanel, P. H. P., and Pokutta, S. (2025). S-DAT: A Multilingual, GenAI-Driven Framework for Automated Divergent Thinking Assessment. Proceedings of the 8th AAAI/ACM Conference on AI, Ethics, and Society (AIES), 8(2), 1194–1205. [PDF] [arXiv] [slides] [poster] creativityhaiimlsocial
  28. Turan, B., Asadulla, S., Steinmann, D., Kersting, K., Stammer, W., and Pokutta, S. (2025). Neural Concept Verifier: Scaling Prover-Verifier Games via Concept Encodings. Accepted for Actionable Interpretability Workshop at ICML 2025. [arXiv] [poster] mlxai
  29. Pauls, J., Zimmer, M., Turan, B., Saatchi, S., Ciais, P., Pokutta, S., and Gieseke, F. (2025). Capturing Temporal Dynamics in Large-Scale Canopy Tree Height Estimation. Proceedings of the 42nd International Conference on Machine Learning (ICML), 267, 48422–48438. [PDF] [arXiv] [visuals] ai4sciencemlsustainability
  30. Hendrych, D., Besançon, M., Martínez-Rubio, D., and Pokutta, S. (2025). Secant Line Search for Frank-Wolfe Algorithms. Proceedings of the 42nd International Conference on Machine Learning (ICML), 267, 23005–23029. [PDF] [arXiv] opt
  31. Mundinger, K., Zimmer, M., Kiem, A., Spiegel, C., and Pokutta, S. (2025). Neural Discovery in Mathematics: Do Machines Dream of Colored Planes? Proceedings of the 42nd International Conference on Machine Learning (ICML), 267, 45236–45255. [PDF] [arXiv] ai4mathai4sciencedggraphs (Oral Presentation + Conference Proceedings)
  32. Pelleriti, N., Zimmer, M., Wirth, E., and Pokutta, S. (2025). Approximating Latent Manifolds in Neural Networks via Vanishing Ideals. Proceedings of the 42nd International Conference on Machine Learning (ICML), 267, 48734–48761. [PDF] [arXiv] compalgmltheory
  33. Roux, C., Martínez-Rubio, D., and Pokutta, S. (2025). Implicit Riemannian Optimism with Applications to Min-Max Problems. Proceedings of the 42nd International Conference on Machine Learning (ICML), 267, 52139–52172. [PDF] [arXiv] mlopt
  34. Troppens, H., Besançon, M., Wilken, S. E., and Pokutta, S. (2025). Mixed-Integer Optimization for Loopless Flux Distributions in Metabolic Networks. 23rd International Symposium on Experimental Algorithms (SEA 2025), 338, 26:1–26:18. [PDF] [arXiv] ai4sciencebiochemistryopt
  35. 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
  36. 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
  37. Wirth, E., Besançon, M., and Pokutta, S. (2025). The Pivoting Framework: Frank-Wolfe Algorithms with Active Set Size Control. Proceedings of the 28th International Conference on Artificial Intelligence and Statistics (AISTATS), 258, 271–279. [PDF] [arXiv] mlopt (Oral Presentation + Conference Proceedings)
  38. Sadiku, S., Wagner, M., Nagarajan, S. G., and Pokutta, S. (2025). S-CFE: Simple Counterfactual Explanations. Proceedings of the 28th International Conference on Artificial Intelligence and Statistics (AISTATS), 258. [PDF] [arXiv] mlxai
  39. Martinez-Rubio, D., Roux, C., Criscitiello, C., and Pokutta, S. (2025). Accelerated Methods for Riemannian Min-Max Problems. Proceedings of the 28th International Conference on Artificial Intelligence and Statistics (AISTATS), 258, 280–288. [PDF] [arXiv] mlopt
  40. Sadiku, S., Wagner, M., and Pokutta, S. (2025). Group-wise Sparse and Explainable Adversarial Attacks. Proceedings of the International Conference on Learning Representations (ICLR). [PDF] [arXiv] [poster] ml
  41. Roux, C., Zimmer, M., and Pokutta, S. (2025). On the Byzantine-Resilience of Distillation-Based Federated Learning. Proceedings of the International Conference on Learning Representations (ICLR). [PDF] [arXiv] [summary] [code] mlopt
  42. Martinez-Rubio, D., Roux, C., and Pokutta, S. (2024). Convergence and Trade-Offs in Riemannian Gradient Descent and Riemannian Proximal Point. Proceedings of ICML. [PDF] [arXiv] mlopt
  43. 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. Proceedings of ICML. [PDF] [arXiv] [code] [visuals] ai4sciencemlsustainability
  44. Kiem, A., Pokutta, S., and Spiegel, C. (2024). Categorification of Flag Algebras. Proceedings of Discrete Mathematics Days. [arXiv] combinatoricsgraphs
  45. Kiem, A., Pokutta, S., and Spiegel, C. (2024). The Four-Color Ramsey Multiplicity of Triangles. Proceedings of Discrete Mathematics Days. [PDF] [arXiv] [code] combinatoricsgraphs
  46. Mundinger, K., Pokutta, S., Spiegel, C., and Zimmer, M. (2024). Extending the Continuum of Six-Colorings. Proceedings of Discrete Mathematics Days. [arXiv] [summary] [slides] ai4mathai4sciencedggraphs
  47. Hendrych, D., Besançon, M., and Pokutta, S. (2024). Solving the Optimal Experiment Design Problem with Mixed-Integer Convex Methods. Proceedings of Symposium on Experimental Algorithms (SEA). [PDF] [arXiv] [code] ipopt
  48. 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] ai4scienceml
  49. Zimmer, M., Spiegel, C., and Pokutta, S. (2024). Sparse Model Soups: A Recipe for Improved Pruning via Model Averaging. Proceedings of ICLR. [PDF] [arXiv] llmmlpruningsparsity
  50. Wäldchen, S., Sharma, K., Turan, B., Zimmer, M., and Pokutta, S. (2024). Interpretability Guarantees with Merlin-Arthur Classifiers. Proceedings of AISTATS. [PDF] [arXiv] mlxai
  51. Thuerck, D., Sofranac, B., Pfetsch, M., and Pokutta, S. (2023). Learning Cuts via Enumeration Oracles. Proceedings of NeurIPS. [PDF] [arXiv] ipmlopt
  52. Martinez-Rubio, D., Wirth, E., and Pokutta, S. (2023). Accelerated and Sparse Algorithms for Approximate Personalized PageRank and Beyond. Proceedings of COLT. [PDF] [arXiv] [slides] [poster] opt
  53. Martinez-Rubio, D., Roux, C., Criscitiello, C., and Pokutta, S. (2023). Accelerated Methods for Riemannian Min-Max Optimization Ensuring Bounded Geometric Penalties. NeurIPS OPT 2023 Workshop. [arXiv] mlopt
  54. Martinez-Rubio, D., and Pokutta, S. (2023). Accelerated Riemannian Optimization: Handling Constraints to Bound Geometric Penalties. Proceedings of COLT. [PDF] [arXiv] [poster] mlopt
  55. Wirth, E., Kerdreux, T., and Pokutta, S. (2023). Acceleration of Frank-Wolfe algorithms with open loop step-sizes. Proceedings of AISTATS. [PDF] [arXiv] [poster] mlopt
  56. Chmiela, A., Gleixner, A., Lichocki, P., and Pokutta, S. (2023). Online Learning for Scheduling MIP Heuristics. Proceedings of CPAIOR. [arXiv] ipmlopt
  57. Wirth, E., Kera, H., and Pokutta, S. (2023). Approximate Vanishing Ideal Computations at Scale. Proceedings of ICLR. [PDF] [arXiv] [slides] [poster] compalgmlopt
  58. Zimmer, M., Spiegel, C., and Pokutta, S. (2023). How I Learned to Stop Worrying and Love Retraining. Proceedings of ICLR. [PDF] [arXiv] [poster] [code] mlpruningsparsity
  59. Parczyk, O., Pokutta, S., Spiegel, C., and Szabó, T. (2022). Fully Computer-Assisted Proofs in Extremal Combinatorics. Proceedings of AAAI. [PDF] [arXiv] [slides] ai4mathai4sciencecombinatoricsgraphs
  60. Martinez-Rubio, D., and Pokutta, S. (2022). Accelerated Riemannian Optimization: Handling Constraints to Bound Geometric Penalties. NeurIPS OPT 2022 Workshop. [arXiv] [poster] mlopt
  61. Criado, F., Martinez-Rubio, D., and Pokutta, S. (2022). Fast Algorithms for Packing Proportional Fairness and its Dual. Proceedings of NeurIPS. [PDF] [arXiv] [poster] [video] mlopt
  62. Parczyk, O., Pokutta, S., Spiegel, C., and Szabó, T. (2022). New Ramsey Multiplicity Bounds and Search Heuristics. Proceedings of Discrete Mathematics Days. [arXiv] [slides] [code] ai4mathai4sciencecombinatorics
  63. Macdonald, J., Besançon, M. E., and Pokutta, S. (2022). Interpretable Neural Networks with Frank-Wolfe: Sparse Relevance Maps and Relevance Orderings. Proceedings of ICML, 162, 14699–14716. [PDF] [arXiv] [poster] [video] mlxai
  64. Wäldchen, S., Huber, F., and Pokutta, S. (2022). Training Characteristic Functions with Reinforcement Learning: XAI-methods play Connect Four. Proceedings of ICML. [PDF] [arXiv] [poster] [video] mlxai (Oral Presentation + Conference Proceedings)
  65. Tsuji, K., Tanaka, K., and Pokutta, S. (2022). Pairwise Conditional Gradients without Swap Steps and Sparser Kernel Herding. Proceedings of ICML. [PDF] [arXiv] [summary] [slides] [code] [video] mlopt
  66. 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. Proceedings of Machine Learning Research, 176, 220–231. [arXiv] mlopt
  67. Wirth, E., and Pokutta, S. (2022). Conditional Gradients for the Approximate Vanishing Ideal. Proceedings of AISTATS. [PDF] [arXiv] [summary] [poster] [code] compalgmlopt
  68. Sofranac, B., Gleixner, A., and Pokutta, S. (2021). An Algorithm-Independent Measure of Progress for Linear Constraint Propagation. Proceedings of International Conference on Principles and Practice of Constraint Programming. [arXiv] [video] hpcipopt
  69. Carderera, A., Besançon, M., and Pokutta, S. (2021). Simple steps are all you need: Frank-Wolfe and generalized self-concordant functions. Proceedings of NeurIPS, 34, 5390–5401. [PDF] [arXiv] [summary] [slides] [poster] [code] mlopt
  70. Chmiela, A., Khalil, E., Gleixner, A., Lodi, A., and Pokutta, S. (2021). Learning to Schedule Heuristics in Branch-and-Bound. Proceedings of NeurIPS. [PDF] [arXiv] [summary] [poster] ipopt
  71. Carderera, A., Diakonikolas, J., Lin, C. Y., and Pokutta, S. (2021). Parameter-free Locally Accelerated Conditional Gradients. Proceedings of ICML. [PDF] [arXiv] [slides] mlopt
  72. Kerdreux, T., d’Aspremont, A., and Pokutta, S. (2021). Projection-Free Optimization on Uniformly Convex Sets. Proceedings of AISTATS. [PDF] [arXiv] [summary] [slides] mlopt (Oral Presentation + Conference Proceedings)
  73. Sofranac, B., Gleixner, A., and Pokutta, S. (2020). Accelerating Domain Propagation: an Efficient GPU-Parallel Algorithm over Sparse Matrices. Proceedings of IA3 at SC20. [arXiv] [summary] [slides] [video] hpcipopt
  74. Pokutta, S. (2020). Restarting Algorithms: Sometimes there is Free Lunch. Proceedings of CPAIOR. [arXiv] [slides] [video] ipopt (Invited Paper)
  75. Mortagy, H., Gupta, S., and Pokutta, S. (2020). Walking in the Shadow: A New Perspective on Descent Directions for Constrained Minimization. Proceedings of NeurIPS. [PDF] [arXiv] [slides] [poster] [code] [video] mlopt
  76. Combettes, C. W., and Pokutta, S. (2020). Boosting Frank-Wolfe by Chasing Gradients. Proceedings of ICML. [PDF] [arXiv] [summary] [slides] [code] [video] mlopt
  77. Pfetsch, M., and Pokutta, S. (2020). IPBoost – Non-Convex Boosting via Integer Programming. Proceedings of ICML. [PDF] [arXiv] [summary] [slides] [code] ipmlopt
  78. Pokutta, S., Singh, M., and Torrico, A. (2020). On the Unreasonable Effectiveness of the Greedy Algorithm: Greedy Adapts to Sharpness. Proceedings of ICML. [PDF] [arXiv] [summary] [slides] [poster] [video] ipmlopt
  79. Diakonikolas, J., Carderera, A., and Pokutta, S. (2020). Locally Accelerated Conditional Gradients. Proceedings of AISTATS, 108, 1737–1747. [PDF] [arXiv] [summary] [slides] [code] [video] mlopt
  80. Pokutta, S., Singh, M., and Torrico, A. (2019). On the Unreasonable Effectiveness of the Greedy Algorithm: Greedy Adapts to Sharpness. OPTML Workshop Paper. [PDF] [summary] [poster] ipopt
  81. Braun, G., Pokutta, S., Tu, D., and Wright, S. (2019). Blended Conditional Gradients: the unconditioning of conditional gradients. Proceedings of ICML. [PDF] [arXiv] [summary] [slides] [poster] [code] mlopt
  82. Diakonikolas, J., Carderera, A., and Pokutta, S. (2019). Breaking the Curse of Dimensionality (Locally) to Accelerate Conditional Gradients. OPTML Workshop Paper. [PDF] [arXiv] [summary] [slides] [poster] [code] mlopt
  83. Combettes, C. W., and Pokutta, S. (2019). Blended Matching Pursuit. Proceedings of NeurIPS. [PDF] [arXiv] [summary] [slides] [poster] [code] mlopt
  84. Anari, N., Haghtalab, N., Naor, S., Pokutta, S., Singh, M., and Torrico, A. (2019). Structured Robust Submodular Maximization: Offline and Online Algorithms. Proceedings of AISTATS. [PDF] [arXiv] optrobopt
  85. Kerdreux, T., d’Aspremont, A., and Pokutta, S. (2019). Restarting Frank-Wolfe. Proceedings of AISTATS. [PDF] [arXiv] [summary] [slides] mlopt
  86. Pokutta, S., Singh, M., and Torrico, A. (2018). Efficient algorithms for robust submodular maximization under matroid constraints. ICML Workshop Paper. [PDF] [arXiv] mloptrobopt
  87. Inanlouganji, A., Pedrielli, G., Fainekos, G., and Pokutta, S. (2018). Continuous Simulation Optimization with Model Mismatch Using Gaussian Process Regression. Proceedings of the 2018 Winter Simulation Conference. optsimulation
  88. Roy, A., Xu, H., and Pokutta, S. (2017). Reinforcement Learning under Model Mismatch. Proceedings of NIPS. [PDF] [arXiv] mlopt
  89. Bärmann, A., Pokutta, S., and Schneider, O. (2017). Emulating the Expert: Inverse Optimization through Online Learning. Proceedings of the International Conference on Machine Learning (ICML). [PDF] [arXiv] [summary] [slides] [poster] [video] ipmlopt
  90. Lan, G., Pokutta, S., Zhou, Y., and Zink, D. (2017). Conditional Accelerated Lazy Stochastic Gradient Descent. Proceedings of the International Conference on Machine Learning (ICML). [PDF] [arXiv] [poster] mlopt
  91. Braun, G., Pokutta, S., and Zink, D. (2017). Lazifying Conditional Gradient Algorithms. Proceedings of the International Conference on Machine Learning (ICML), 70, 566–575. [PDF] [arXiv] [slides] [poster] mlopt
  92. Arumugam, K., Kadampot, I., Tahmasbi, M., Shah, S., Bloch, M., and Pokutta, S. (2017). Modulation Recognition Using Side Information and Hybrid Learning. Proceedings of IEEE DySPAN. mloptsignalprocessing
  93. Braun, G., Roy, A., and Pokutta, S. (2016). Stronger Reductions for Extended Formulations. Proceedings of IPCO. [arXiv] extendedformulationipopt
  94. Braun, G., Brown-Cohen, J., Huq, A., Pokutta, S., Raghavendra, P., Roy, A., Weitz, B., and Zink, D. (2016). The matching problem has no small symmetric SDP. Proceedings of SODA 2016. [PDF] [arXiv] extendedformulationipopt
  95. Roy, A., and Pokutta, S. (2016). Hierarchical Clustering via Spreading Metrics. Proceedings of NIPS. [PDF] [arXiv] mlopt (Oral Presentation + Conference Proceedings)
  96. Xie, Y., Li, Q., and Pokutta, S. (2015). Supervised Online Subspace Tracking. Proceedings of Asilomar Conference on Signals, Systems, and Computers. mloptsignalprocessing
  97. Song, R., Xie, Y., and Pokutta, S. (2015). Sequential Sensing with Model Mismatch. Proceedings of ISIT. mloptsignalprocessing
  98. Braun, G., Pokutta, S., and Zink, D. (2015). Inapproximability of combinatorial problems via small LPs and SDPs. Proceeedings of STOC. [arXiv] [video] extendedformulationipopt
  99. Pokutta, S. (2015). Information Theory and Polyhedral Combinatorics. Proceedings of 53rd Annual Allerton Conference on Communication, Control, and Computing. [PDF] extendedformulationinformationtheoryipoptsurvey
  100. Braun, G., and Pokutta, S. (2015). The matching polytope does not admit fully-polynomial size relaxation schemes. Proceeedings of SODA. [arXiv] extendedformulationipopt
  101. Bazzi, A., Fiorini, S., Pokutta, S., and Svensson, O. (2015). Small linear programs cannot approximate Vertex Cover within a factor of 2 - epsilon. Proceedings of FOCS. [arXiv] [slides] extendedformulationipopt
  102. Braun, G., Pokutta, S., and Xie, Y. (2014). Info-Greedy Sequential Adaptive Compressed Sensing. Proceedings of 52nd Annual Allerton Conference on Communication, Control, and Computing. [arXiv] mloptsignalprocessing
  103. Braun, G., Fiorini, S., and Pokutta, S. (2014). Average case polyhedral complexity of the maximum stable set problem. Proceedings of RANDOM. [PDF] [arXiv] extendedformulationipopt
  104. Briët, J., Dadush, D., and Pokutta, S. (2013). On the existence of 0/1 polytopes with high semidefinite extension complexity. Proceedings of ESA. [arXiv] extendedformulationipopt
  105. Braun, G., and Pokutta, S. (2013). Common information and unique disjointness. Foundations of Computer Science (FOCS), 2013 IEEE 54th Annual Symposium, 688–697. [arXiv] extendedformulationinformationtheoryipopt
  106. Schmaltz, C., Pokutta, S., Heidorn, T., and Andrae, S. (2013). How to make regulators and shareholders happy under Basel III. Proceedings of the 26th Australasian Finance and Banking Conference. [arXiv] financeopt
  107. Braun, G., and Pokutta, S. (2012). An algebraic view on symmetric extended formulations. Proceedings of ISCO, Lecture Notes in Computer Science, 7422(141–152). [arXiv] algebraextendedformulationipopt
  108. Braun, G., Fiorini, S., Pokutta, S., and Steurer, D. (2012). Approximation Limits of Linear Programs (Beyond Hierarchies). Proceedings of FOCS. [arXiv] extendedformulationipopt
  109. Fiorini, S., Massar, S., Pokutta, S., Tiwary, H. R., and de Wolf, R. (2012). Linear vs. Semidefinite Extended Formulations: Exponential Separation and Strong Lower Bounds. Proceedings of STOC. [arXiv] extendedformulationiplowerboundsopt (Best paper award at STOC 2012)
  110. Pokutta, S., and Schmaltz, C. (2011). A network model for bank lending capacity. Proceedings of Systemic Risk, Basel III, Financial Stability and Regulation. [arXiv] financeopt
  111. Dey, S. S., and Pokutta, S. (2011). Design and verify: a new scheme for generating cutting-planes. Proceedings of IPCO, Lecture Notes in Computer Science, 6655, 143–155. [arXiv] ipopt
  112. Helmke, H., Gluchshenko, O., Martin, A., Peter, A., Pokutta, S., and Siebert, U. (2011). Optimal Mixed-Mode Runway Scheduling. Proceedings of DACS. [arXiv] ipopttranslog
  113. Pokutta, S., and Schmaltz, C. (2011). Optimal Planning under Basel III Regulations. Proceedings of 24th Australasian Finance and Banking Conference. [arXiv] financeopt
  114. Martin, A., Müller, J., and Pokutta, S. (2010). On clearing coupled day-ahead electricity markets. Proceedings of 23rd Australasian Finance and Banking Conference. [arXiv] energyfinanceopt
  115. Braun, G., and Pokutta, S. (2010). Rank of random half-integral polytopes. Electronic Notes in Discrete Mathematics, 36, 415–422. [PDF] [arXiv] ipoptprobability
  116. Pokutta, S., and Schulz, A. S. (2010). On the rank of generic cutting-plane proof systems. Proceedings of IPCO, Lecture Notes in Computer Science, 6080, 450–463. [PDF] [arXiv] ipopt
  117. Drewes, S., and Pokutta, S. (2010). Geometric mean maximization in the presence of discrete decisions. Proceedings of 23rd Australasian Finance and Banking Conference. financeipopt
  118. Drewes, S., and Pokutta, S. (2010). Cutting-planes for weakly-coupled 0/1 second order cone programs. Electronic Notes in Discrete Mathematics, 36, 735–742. [PDF] [arXiv] ipopt
  119. Pokutta, S., and Schmaltz, C. (2009). Optimal degree of centralization of liquidity management. Proceedings of 22nd Australasian Finance and Banking Conference. [arXiv] financeopt

Refereed Journals ⏵

  1. Meise, I., Pfetsch, M. E., and Pokutta, S. (2026). A Tight Approximability Analysis of Boosting. In C. Bülte, M. Burger, M. Hein, G. Kutyniok, S. Pokutta, & I. Steinwart (Eds.), Theoretical Foundations of Deep Learning. Springer. mlopt
  2. Haase, J., Klessascheck, F., Mendling, J., and Pokutta, S. (2026). Sustainability via LLM Right-sizing. IEEE Transactions on Sustainable Computing. [arXiv] haiimlsustainability
  3. Kreimeier, T., Pokutta, S., Walther, A., and Woodstock, Z. (2026). On a Frank-Wolfe Approach for Abs-smooth Functions. Optimization Methods and Software, 41(2). [arXiv] [poster] mlopt
  4. Kiem, A., Pokutta, S., and Spiegel, C. (2026). The Four-Color Ramsey Multiplicity of Triangles. Journal of Combinatorial Theory, Series B, 179, 19–70. [arXiv] [code] combinatoricsgraphs
  5. Designolle, S., Vértesi, T., and Pokutta, S. (2026). Better bounds on finite-order Grothendieck constants with applications to Bell nonlocality. Physical Review A, 113, 022401. [PDF] [arXiv] optphysicsquantum
  6. Haase, J., and Pokutta, S. (2026). Human–AI Cocreativity: Exploring synergies across levels of creative collaboration. In J. C. Kaufman & M. Worwood (Eds.), Generative Artificial Intelligence and Creativity (pp. 205–221). [PDF] [arXiv] creativityhaiimlsocial
  7. Carderera, A., and Pokutta, S. (2026). Second-order Conditional Gradient Sliding. In Data Science and Optimization (Vol. 91, pp. 303–321). Springer. [arXiv] [summary] [code] mlopt
  8. Göß, A., Martin, A., Pokutta, S., and Sharma, K. (2026). Norm-induced Cuts: Optimization with Lipschitzian Black-box Functions. Journal of Global Optimization. [PDF] [arXiv] ipopt
  9. Kerdreux, T., d’Aspremont, A., and Pokutta, S. (2026). Local and Global Uniform Convexity Conditions. In Data Science and Optimization (Vol. 91, pp. 85–120). Springer. [PDF] [arXiv] mlopt
  10. Wirth, E., Peña, J., and Pokutta, S. (2025). Accelerated Affine-Invariant Convergence Rates of the Frank-Wolfe Algorithm with Open-Loop Step-Sizes. Mathematical Programming, 214(1), 201–245. [PDF] [arXiv] complexityfwopt
  11. 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. Journal of Creativity. [PDF] [arXiv] creativityhaiimlsocial
  12. 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. ACM Transactions on Mathematical Software, 51(4), 1–33. [PDF] [arXiv] optsoftware
  13. Wirth, E., Peña, J., and Pokutta, S. (2025). Fast Convergence of Frank-Wolfe algorithms on polytopes. Mathematics of Operations Research. [PDF] [arXiv] mlopt
  14. 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, & M. Weiser (Eds.), Mathematical Optimization for Machine Learning (pp. 137–168). De Gruyter. [PDF] [arXiv] mloptsparsity
  15. 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. Journal of Computational and Applied Mathematics, 470, 116675. [PDF] [arXiv] [summary] ai4sciencemlopt
  16. Hendrych, D., Troppens, H., Besançon, M., and Pokutta, S. (2025). Convex mixed-integer optimization with Frank-Wolfe methods. Mathematical Programming Computation. [PDF] [arXiv] [slides] [poster] [code] ipminlpoptsoftware
  17. Vu-Han, T.-L., Sunkara, V., Bermudez-Schettino, R., Schwechten, J., Runge, R., Perka, C., Winkler, T., Pokutta, S., Weiß, C., and Pumberger, M. (2025). Feature Engineering for the Prediction of Scoliosis in 5q-Spinal Muscular Atrophy. Journal of Cachexia, Sarcopenia and Muscle, 16(1). [PDF] ai4sciencemedicineml
  18. Woodstock, Z., and Pokutta, S. (2024). Splitting the Conditional Gradient Algorithm. To Appear in SIAM Journal on Optimization. [arXiv] mlopt
  19. 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
  20. Stengl, M., Gelß, P., Klus, S., and Pokutta, S. (2024). Existence and Uniqueness of Solutions of the Koopman–von Neumann Equation on Bounded Domains. Journal of Physics A: Mathematical and Theoretical, 57(39), 395302. [PDF] [arXiv] physics
  21. Deza, A., Onn, S., Pokutta, S., and Pournin, L. (2024). Kissing polytopes. SIAM Journal on Discrete Mathematics, 38(4), 2643–2664. [PDF] [arXiv] dm
  22. Parczyk, O., Pokutta, S., Spiegel, C., and Szabó, T. (2024). New Ramsey Multiplicity Bounds and Search Heuristics. Foundations of Computational Mathematics. [PDF] [arXiv] [slides] [code] ai4mathai4sciencecombinatoricsgraphs
  23. Mundinger, K., Pokutta, S., Spiegel, C., and Zimmer, M. (2024). Extending the Continuum of Six-Colorings. Geombinatorics Quarterly. [arXiv] [summary] [slides] ai4mathai4sciencedggraphs
  24. Carderera, A., Besançon, M., and Pokutta, S. (2024). Scalable Frank-Wolfe on Generalized Self-Concordant Functions via Simple Steps. SIAM Journal on Optimization, 34(3). [PDF] [arXiv] [summary] [slides] [poster] [code] mlopt
  25. Designolle, S., Vértesi, T., and Pokutta, S. (2024). Symmetric multipartite Bell inequalities via Frank-Wolfe algorithms. Physical Review A, 109(2). [PDF] [arXiv] optphysicsquantumsymmetry
  26. Deza, A., Pokutta, S., and Pournin, L. (2024). The complexity of geometric scaling. Operations Research Letters, 52. [PDF] [arXiv] dmopt
  27. Pokutta, S. (2024). The Frank-Wolfe algorithm: a short introduction. Jahresbericht Der Deutschen Mathematiker-Vereinigung, 126, 3–35. [PDF] [arXiv] mlopt
  28. 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. Physical Reviews Research. [PDF] [arXiv] [slides] optphysicsquantum
  29. Bienstock, D., Muñoz, G., and Pokutta, S. (2023). Principled Deep Neural Network Training through Linear Programming. Discrete Optimization, 49. [PDF] [arXiv] [summary] mlopt
  30. Aigner, K.-M., Bärmann, A., Braun, K., Liers, F., Pokutta, S., Schneider, O., Sharma, K., and Tschuppik, S. (2023). Data-driven Distributionally Robust Optimization over Time. INFORMS Journal on Optimization, 5(4). [PDF] [arXiv] ipmloptrobopt
  31. Hunkenschröder, C., Pokutta, S., and Weismantel, R. (2023). Minimizing a low-dimensional convex function over a high-dimensional cube. SIAM Journal on Optimization, 33(2). [PDF] [arXiv] opt
  32. Combettes, C. W., and Pokutta, S. (2023). Revisiting the Approximate Carathéodory Problem via the Frank-Wolfe Algorithm. Mathematical Programming A, 197, 191—214. [PDF] [arXiv] [summary] [slides] [code] [video] opt
  33. Sofranac, B., Gleixner, A., and Pokutta, S. (2022). Accelerating Domain Propagation: an Efficient GPU-Parallel Algorithm over Sparse Matrices. Parallel Computing, 109. [PDF] [arXiv] [summary] [slides] [video] hpcipopt
  34. Sofranac, B., Gleixner, A., and Pokutta, S. (2022). An Algorithm-Independent Measure of Progress for Linear Constraint Propagation. Constraints, 27, 432–455. [PDF] [arXiv] [video] hpcipopt
  35. 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] ai4sciencemedicineml
  36. Besançon, M., Carderera, A., and Pokutta, S. (2022). FrankWolfe.jl: a high-performance and flexible toolbox for Frank-Wolfe algorithms and Conditional Gradients. INFORMS Journal on Computing. [PDF] [arXiv] [summary] [slides] [code] mloptsoftware
  37. Faenza, Y., Muñoz, G., and Pokutta, S. (2022). New Limits of Treewidth-based tractability in Optimization. Mathematical Programming A, 191, 559–594. [PDF] [arXiv] [summary] extendedformulationipopt
  38. Kerdreux, T., d’Aspremont, A., and Pokutta, S. (2022). Restarting Frank-Wolfe: Faster Rates under Hölderian Error Bounds. Journal of Optimization Theory and Applications, 192, 799–829. [PDF] [arXiv] [summary] [slides] mlopt
  39. Combettes, C. W., and Pokutta, S. (2021). Complexity of Linear Minimization and Projection on Some Sets. Operations Research Letters, 49(4). [arXiv] [code] opt
  40. Kerdreux, T., Roux, C., d’Aspremont, A., and Pokutta, S. (2021). Linear Bandits on Uniformly Convex Sets. Journal of Machine Learning Research (JMLR), 22(284), 1–23. [PDF] [arXiv] [summary] mlopt
  41. Anari, N., Haghtalab, N., Naor, S., Pokutta, S., Singh, M., and Torrico, A. (2021). Structured Robust Submodular Maximization: Offline and Online Algorithms. INFORMS Journal on Computing, 33(4), 1259–1684. [PDF] [arXiv] optrobopt
  42. Gatzert, N., Pokutta, S., and Vogl, N. (2019). Convergence of Capital and Insurance Markets: Pricing Aspects of Index-Linked Catastrophic Loss Instruments. Journal of Risk and Insurance, 86, 39–72. [arXiv] finance (Best paper award at European Group of Risk and Insurance Economists Annual Meeting 2014 for conference version)
  43. Braun, G., Pokutta, S., and Zink, D. (2019). Lazifying Conditional Gradient Algorithms. Journal of Machine Learning Research (JMLR), 20(71), 1–42. [PDF] [arXiv] [slides] mlopt
  44. Bazzi, A., Fiorini, S., Pokutta, S., and Svensson, O. (2019). Small linear programs cannot approximate Vertex Cover within a factor of 2 - epsilon. Mathematics of Operations Research, 44(1), 1–375. [arXiv] [slides] extendedformulationipopt
  45. Braun, G., Pokutta, S., and Zink, D. (2019). Affine Reductions for LPs and SDPs. Mathematical Programming A, 173(1), 281–312. [PDF] [arXiv] extendedformulationipopt
  46. Le Bodic, P., Pfetsch, M., Pavelka, J., and Pokutta, S. (2018). Solving MIPs via Scaling-based Augmentation. Discrete Optimization, 27, 1–25. [PDF] [arXiv] ipopt
  47. Bodur, M., Del Pia, A., Dey, S. S., Molinaro, M., and Pokutta, S. (2018). Aggregation-based cutting-planes for packing and covering Integer Programs. Mathematical Programming A, 171, 331–359. [PDF] [arXiv] ipopt
  48. Song, R., Xie, Y., and Pokutta, S. (2018). On the effect of model mismatch for sequential Info-Greedy Sensing. EURASIP Journal on Advances in Signal Processing. [PDF] informationtheorymloptsignalprocessing
  49. Knueven, B., Ostrowski, J., and Pokutta, S. (2018). Detecting Almost Symmetries in Graphs. Mathematical Programming C, 10, 143–185. [PDF] [arXiv] graphsipoptsymmetry
  50. Braun, G., Roy, A., and Pokutta, S. (2018). Stronger Reductions for Extended Formulations. Mathematical Programming B, 172, 591–620. [arXiv] extendedformulationipopt
  51. Christensen, H., Khan, A., Pokutta, S., and Tetali, P. (2017). Approximation and online algorithms for multidimensional bin packing: A survey. Computer Science Review, 24, 63–79. [PDF] ipoptsurvey
  52. Roy, A., and Pokutta, S. (2017). Hierarchical Clustering via Spreading Metrics. Journal of Machine Learning Research (JMLR), 18, 1–35. [PDF] [arXiv] mlopt
  53. Braun, G., Guzmán, C., and Pokutta, S. (2017). Unifying Lower Bounds on the Oracle Complexity of Nonsmooth Convex Optimization. IEEE Transactions of Information Theory, 63(7), 4709–4724. [PDF] [arXiv] complexityinformationtheorylowerboundsopt
  54. Braun, G., Jain, R., Lee, T., and Pokutta, S. (2017). Information-theoretic approximations of the nonnegative rank. Computational Complexity, 26(1), 147–197. [arXiv] extendedformulationinformationtheory
  55. Braun, G., Brown-Cohen, J., Huq, A., Pokutta, S., Raghavendra, P., Roy, A., Weitz, B., and Zink, D. (2017). The matching problem has no small symmetric SDP. Mathematical Programming A, 165(2), 643–662. [PDF] [arXiv] extendedformulationipoptsymmetry
  56. Martin, A., Müller, J., Pape, S., Peter, A., Pokutta, S., and Winter, T. (2017). Pricing and clearing combinatorial markets with singleton and swap orders. Mathematical Methods of Operations Research, 85(2), 155–177. [arXiv] financeipopt
  57. Braun, G., and Pokutta, S. (2016). A polyhedral characterization of Border Bases. SIAM Journal on Discrete Mathematics, 30(1), 239–265. [arXiv] algebracompalgipopt
  58. Bärmann, A., Heidt, A., Martin, A., Pokutta, S., and Thurner, C. (2016). Polyhedral Approximation of Ellipsoidal Uncertainty Sets via Extended Formulations - a computational case study. Computational Management Science, 13(2), 151–193. [PDF] [arXiv] extendedformulationipopt
  59. Braun, G., and Pokutta, S. (2016). Common information and unique disjointness. Algorithmica, 76(3), 597–629. [PDF] [arXiv] extendedformulationinformationtheoryipopt (Invited to Special Issue of Algorithmica)
  60. Braun, G., Fiorini, S., and Pokutta, S. (2016). Average case polyhedral complexity of the maximum stable set problem. Mathematical Programming A, 160(1), 407–431. [PDF] [arXiv] extendedformulationipopt
  61. Braun, G., Pokutta, S., and Xie, Y. (2015). Info-Greedy Sequential Adaptive Compressed Sensing. IEEE Journal of Selected Topics in Signal Processing, 9(4), 601–611. [arXiv] informationtheoryoptsignalprocessing
  62. Braun, G., Fiorini, S., Pokutta, S., and Steurer, D. (2015). Approximation Limits of Linear Programs (Beyond Hierarchies). Mathematics of Operations Research, 40(3), 179–199. [arXiv] extendedformulationipopt
  63. Braun, G., and Pokutta, S. (2015). The matching polytope does not admit fully-polynomial size relaxation schemes. IEEE Transactions on Information Theory, 61(10), 1–11. [PDF] [arXiv] extendedformulationinformationtheoryipopt
  64. Briët, J., Dadush, D., and Pokutta, S. (2015). On the existence of 0/1 polytopes with high semidefinite extension complexity. Mathematical Programming B, 153(1), 179–199. [arXiv] extendedformulationipopt
  65. Fiorini, S., Massar, S., Pokutta, S., Tiwary, H. R., and de Wolf, R. (2015). Exponential Lower Bounds for Polytopes in Combinatorial Optimization. Journal of the ACM, 62(2), 1–17. [PDF] [arXiv] extendedformulationiplowerboundsopt
  66. Drewes, S., and Pokutta, S. (2014). Symmetry-exploiting cuts for a class of mixed-0/1 second order cone programs. Discrete Optimization, 13, 23–35. [arXiv] ipoptsymmetry
  67. Drewes, S., and Pokutta, S. (2014). Computing discrete expected utility maximizing portfolios. Journal of Investing, 23(4), 121–132. [arXiv] financeipopt
  68. Braun, G., and Pokutta, S. (2014). A short proof for the polyhedrality of the Chvátal-Gomory closure of a compact convex set. Operations Research Letters, 42, 307–310. [arXiv] ipopt
  69. Schmaltz, C., Pokutta, S., Heidorn, T., and Andrae, S. (2014). How to make regulators and shareholders happy under Basel III. Journal of Banking and Finance, 311–325. [PDF] [arXiv] financeopt
  70. Martin, A., Müller, J., and Pokutta, S. (2014). Strict linear prices in non-convex European day-ahead electricity markets. Optimization Methods and Software, 29(1), 189–221. [PDF] [arXiv] energyfinanceopt (Best paper award at Energy Finance 2010 for conference version)
  71. Dey, S. S., and Pokutta, S. (2014). Design and verify: a new scheme for generating cutting-planes. Mathematical Programming A, 145, 199–222. [arXiv] ipopt
  72. Pokutta, S., and Van Vyve, M. (2013). A note on the extension complexity of the knapsack polytope. Operations Research Letters, 41, 347–350. [PDF] [arXiv] ipopt
  73. Kroll, C., and Pokutta, S. (2013). Just a perfect day: developing a happiness optimised day schedule. Journal of Economic Psychology, 34, 210–217. [PDF] [video] optsocial
  74. Pokutta, S., and Schmaltz, C. (2012). Optimal Planning under Basel III Regulations. Cass-Capco Institute Paper Series on Risk, 34. [PDF] [arXiv] financeopt
  75. Braun, G., and Pokutta, S. (2012). Rigid abelian groups and the probabilistic method. Contemporary Mathematics, 576, 17–30. [PDF] [arXiv] algebraprobability
  76. Göbel, R., and Pokutta, S. (2012). Absolutely rigid fields and Shelah’s absolutely rigid trees. Contemporary Mathematics, 576, 105–128. [PDF] [arXiv] algebrasettheory
  77. Haus, U. U., Hemmecke, R., and Pokutta, S. (2011). Reconstructing biochemical cluster networks. Journal of Mathematical Chemistry, 49(10), 2441–2456. [PDF] [arXiv] algebrabiochemistry
  78. Braun, G., and Pokutta, S. (2011). Random half-integral polytopes. Operations Research Letters, 39(3), 204–207. [arXiv] ipoptprobability
  79. Letchford, A. N., Pokutta, S., and Schulz, A. S. (2011). On the membership problem for the 0,1/2-closure. Operations Research Letters, 39(5), 301–304. [PDF] [arXiv] ipopt
  80. Pokutta, S., and Schulz, A. S. (2011). Integer-empty polytopes in the 0/1-cube with maximal Gomory-Chvátal rank. Operations Research Letters, 39(6), 457–460. [PDF] [arXiv] ipopt
  81. Pokutta, S., and Stauffer, G. (2011). Lower bounds for the Chvátal-Gomory rank in the 0/1 cube. Operations Research Letters, 39(3), 200–203. [PDF] [arXiv] iplowerboundsopt
  82. Pokutta, S., and Schmaltz, C. (2011). Managing liquidity: Optimal degree of centralization. Journal of Banking and Finance, 35, 627–638. [PDF] [arXiv] financeopt (Cited by the Committee on the Global Financial System in CGFS Papers No 39)
  83. Heldt, D., Kreuzer, M., Pokutta, S., and Poulisse, H. (2009). Approximate Computation of zero-dimensional polynomial ideals. Journal of Symbolic Computation, 44, 1566–1591. [PDF] algebracompalg
  84. Pokutta, S., and Stauffer, G. (2009). France Telecom Workforce Scheduling Problem: a challenge. RAIRO-Operations Research, 43, 375–386. [PDF] ipopt
  85. Göbel, R., and Pokutta, S. (2008). Construction of dual modules using Martin’s axiom. Journal of Algebra, 320, 2388–2404. [PDF] algebrasettheory
  86. Droste, M., Göbel, R., and Pokutta, S. (2008). Absolute graphs with prescribed endomorphism monoid. Semigroup Forum, 76, 256–267. [PDF] algebragraphssettheory
  87. Pokutta, S., and Strüngmann, L. (2007). The Chase radical and reduced products. Journal of Pure and Applied Algebra, 211, 532–540. [PDF] algebrasettheory

Unpublished Manuscripts ⏵

  1. Roux, C., Wirth, E., Pokutta, S., and Kerdreux, T. (2021). Efficient Online-Bandit Strategies for Minimax Learning Problems. Preprint. [arXiv] mlopt
  2. Pokutta, S., and Xu, H. (2021). Adversaries in Online Learning Revisited: with applications in Robust Optimization and Adversarial training. Preprint. [arXiv] mloptrobopt
  3. Braun, G., and Pokutta, S. (2021). Dual Prices for Frank-Wolfe Algorithms. Preprint. [arXiv] opt
  4. Braun, G., and Pokutta, S. (2016). An efficient high-probability algorithm for Linear Bandits. Preprint. [arXiv] mlopt
  5. Braun, G., and Pokutta, S. (2015). An information diffusion Fano inequality. Preprint. [arXiv] informationtheorysignalprocessing
  6. Pokutta, S., and Schulz, A. S. (2013). On the rank of cutting-plane proof systems. Preprint. [arXiv] ipopt
  7. Braun, G., and Pokutta, S. (2012). An algebraic view on symmetric extended formulations. Preprint. [arXiv] algebraextendedformulationipopt
  8. Pokutta, S., Schmaltz, C., and Stiller, S. (2011). Measuring Systemic Risk and Contagion in Financial Networks. Preprint. [arXiv] financeopt
  9. Pokutta, S. (2011). Lower bounds for Chvátal-Gomory style operators. Preprint. [arXiv] iplowerboundsopt
  10. Pokutta, S., and Schulz, A. S. (2009). On the connection of the Sherali-Adams closure and border bases. Preprint. [arXiv] compalgipopt
  11. Pokutta, S. (2008). Stowage optimization for inland vessels. Preprint. ipopttranslog

Other ⏵

  1. Pokutta, S. (2026). Eine (kurze) Einführung in Large Language Models für Interessierte (German). In E. Ottschofski, M. Wildner, & T. Pop (Eds.), Der Traum der Gurke (pp. 13–32). Pop Verlag Ludwigsburg. llmmloutreachpopular
  2. Pokutta, S. (2021). Mathematik, Machine Learning und Artificial Intelligence. Mitteilungen Der DMV (German). [PDF] optoutreach
  3. Collier, V., Ostrowski, J., and Pokutta, S. (2015). A Symmetric Extended Formulation of the Bin Packing Problem. Proceedings of IIE Annual Conference. extendedformulationipoptsymmetry (Paper won second place in the Undergraduate Research Operations Research competition)
  4. Lee, D., and Pokutta, S. (2015). Toward a Science of Autonomy for Physical Systems: Transportation. Computing Community Consortium White Paper. [PDF] autonomousoutreachtranslog
  5. Alf, M., and Pokutta, S. (2006). How logistics service providers can make use of the real options concept. Symposium Mathematik & Logistik, Bad Honnef 2005, Conference Proceedings. outreachtranslog
  6. Heldt, D., Kreuzer, M., Pokutta, S., and Poulisse, H. (2006). Algebraische Modellierung mit Methoden der approximativen Computer Algebra und Anwendungen in der Ölindustrie. OR News, 15–18. compalgoutreach
  7. Pokutta, S. (2005). Products over countable domains [PhD thesis]. In PhD thesis. University of Duisburg-Essen. algebrasettheory
  8. Pokutta, S., and Törner, G. (2005). Fixpunktminimierung bei Binnenschiffen. OR News, 23, 13–17. ipoptoutreachtranslog
  9. Pokutta, S. (2003). Generalizations of the Chase radical and direct products [Master's thesis]. In Diploma thesis. University of Duisburg-Essen. algebrasettheory