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
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. To Appear in Proceedings of ICML.
[arXiv]
[visuals]
ai4sciencemlsustainability
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
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)
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
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
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
Sadiku, S., Wagner, M., and Pokutta, S. (2025). Group-wise Sparse and Explainable Adversarial Attacks. To Appear in Proceedings of ICLR.
[arXiv]
[poster]
ml
Roux, C., Zimmer, M., and Pokutta, S. (2025). On the Byzantine-Resilience of Distillation-Based Federated Learning. To Appear in Proceedings of ICLR.
[arXiv]
[summary]
[code]
mlopt
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
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.
[arXiv]
[code]
[visuals]
ai4sciencemlsustainability
Kiem, A., Pokutta, S., and Spiegel, C. (2024). Categorification of Flag Algebras. Proceedings of Discrete Mathematics Days.
[arXiv]
combinatoricsgraphs
Kiem, A., Pokutta, S., and Spiegel, C. (2024). The Four-Color Ramsey Multiplicity of Triangles. Proceedings of Discrete Mathematics Days.
[PDF]
[arXiv]
[code]
combinatoricsgraphs
Mundinger, K., Pokutta, S., Spiegel, C., and Zimmer, M. (2024). Extending the Continuum of Six-Colorings. Proceedings of Discrete Mathematics Days.
[arXiv]
[summary]
[slides]
ai4sciencedggraphs
Martinez-Rubio, D., Roux, C., and Pokutta, S. (2024). Convergence and Trade-Offs in Riemannian Gradient Descent and Riemannian Proximal Point. Proceedings of ICML.
[arXiv]
mlopt
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
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
Zimmer, M., Spiegel, C., and Pokutta, S. (2024). Sparse Model Soups: A Recipe for Improved Pruning via Model Averaging. Proceedings of ICLR.
[arXiv]
mlsparsity
Wäldchen, S., Sharma, K., Turan, B., Zimmer, M., and Pokutta, S. (2024). Interpretability Guarantees with Merlin-Arthur Classifiers. Proceedings of AISTATS.
[arXiv]
mlxai
Thuerck, D., Sofranac, B., Pfetsch, M., and Pokutta, S. (2023). Learning Cuts via Enumeration Oracles. Proceedings of NeurIPS.
[arXiv]
ipmlopt
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
Martinez-Rubio, D., Wirth, E., and Pokutta, S. (2023). Accelerated and Sparse Algorithms for Approximate Personalized PageRank and Beyond. Proceedings of COLT.
[arXiv]
[slides]
[poster]
opt
Martinez-Rubio, D., and Pokutta, S. (2023). Accelerated Riemannian Optimization: Handling Constraints to Bound Geometric Penalties. Proceedings of COLT.
[arXiv]
[poster]
mlopt
Wirth, E., Kera, H., and Pokutta, S. (2023). Approximate Vanishing Ideal Computations at Scale. Proceedings of ICLR.
[arXiv]
[slides]
[poster]
compalgmlopt
Zimmer, M., Spiegel, C., and Pokutta, S. (2023). How I Learned to Stop Worrying and Love Retraining. Proceedings of ICLR.
[arXiv]
[poster]
[code]
mlsparsity
Chmiela, A., Gleixner, A., Lichocki, P., and Pokutta, S. (2023). Online Learning for Scheduling MIP Heuristics. Proceedings of CPAIOR.
[arXiv]
ipmlopt
Wirth, E., Kerdreux, T., and Pokutta, S. (2023). Acceleration of Frank-Wolfe algorithms with open loop step-sizes. Proceedings of AISTATS.
[arXiv]
[poster]
mlopt
Parczyk, O., Pokutta, S., Spiegel, C., and Szabó, T. (2022). Fully Computer-Assisted Proofs in Extremal Combinatorics. Proceedings of AAAI.
[arXiv]
[slides]
ai4sciencecombinatoricsgraphs
Martinez-Rubio, D., and Pokutta, S. (2022). Accelerated Riemannian Optimization: Handling Constraints to Bound Geometric Penalties. NeurIPS OPT 2022 Workshop.
[arXiv]
[poster]
mlopt
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
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]
ai4sciencecombinatorics
Macdonald, J., Besançon, M., and Pokutta, S. (2022). Interpretable Neural Networks with Frank-Wolfe: Sparse Relevance Maps and Relevance Orderings. Proceedings of ICML.
[arXiv]
[poster]
[video]
mlxai
Wäldchen, S., Huber, F., and Pokutta, S. (2022). Training Characteristic Functions with Reinforcement Learning: XAI-methods play Connect Four. Proceedings of ICML.
[arXiv]
[poster]
[video]
mlxai
(Oral Presentation + Conference Proceedings)
Tsuji, K., Tanaka, K., and Pokutta, S. (2022). Pairwise Conditional Gradients without Swap Steps and Sparser Kernel Herding. Proceedings of ICML.
[arXiv]
[summary]
[slides]
[code]
[video]
mlopt
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
Wirth, E., and Pokutta, S. (2022). Conditional Gradients for the Approximate Vanishing Ideal. Proceedings of AISTATS.
[arXiv]
[summary]
[poster]
[code]
compalgmlopt
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
Carderera, A., Besançon, M., and Pokutta, S. (2021). Simple steps are all you need: Frank-Wolfe and generalized self-concordant functions. Proceedings of NeurIPS.
[arXiv]
[summary]
[slides]
[poster]
[code]
mlopt
Chmiela, A., Khalil, E., Gleixner, A., Lodi, A., and Pokutta, S. (2021). Learning to Schedule Heuristics in Branch-and-Bound. Proceedings of NeurIPS.
[arXiv]
[summary]
[poster]
ipopt
Carderera, A., Diakonikolas, J., Lin, C. Y., and Pokutta, S. (2021). Parameter-free Locally Accelerated Conditional Gradients. Proceedings of ICML.
[arXiv]
[slides]
mlopt
Kerdreux, T., d’Aspremont, A., and Pokutta, S. (2021). Projection-Free Optimization on Uniformly Convex Sets. Proceedings of AISTATS.
[arXiv]
[summary]
[slides]
mlopt
(Oral Presentation + Conference Proceedings)
Pokutta, S. (2020). Restarting Algorithms: Sometimes there is Free Lunch. Proceedings of CPAIOR.
[arXiv]
[slides]
[video]
ipopt
(Invited Paper)
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
Mortagy, H., Gupta, S., and Pokutta, S. (2020). Walking in the Shadow: A New Perspective on Descent Directions for Constrained Minimization. Proceedings of NeurIPS.
[arXiv]
[slides]
[poster]
[code]
[video]
mlopt
Combettes, C. W., and Pokutta, S. (2020). Boosting Frank-Wolfe by Chasing Gradients. Proceedings of ICML.
[PDF]
[arXiv]
[summary]
[slides]
[code]
[video]
mlopt
Pokutta, S., Singh, M., and Torrico, A. (2020). On the Unreasonable Effectiveness of the Greedy Algorithm: Greedy Adapts to Sharpness. Proceedings of ICML.
[arXiv]
[summary]
[slides]
[poster]
[video]
ipmlopt
Diakonikolas, J., Carderera, A., and Pokutta, S. (2020). Locally Accelerated Conditional Gradients. Proceedings of AISTATS.
[PDF]
[arXiv]
[summary]
[slides]
[code]
[video]
mlopt
Pfetsch, M., and Pokutta, S. (2020). IPBoost – Non-Convex Boosting via Integer Programming. Proceedings of ICML.
[arXiv]
[summary]
[slides]
[code]
ipmlopt
Combettes, C. W., and Pokutta, S. (2019). Blended Matching Pursuit. Proceedings of NeurIPS.
[PDF]
[arXiv]
[summary]
[slides]
[poster]
[code]
mlopt
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
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
Kerdreux, T., d’Aspremont, A., and Pokutta, S. (2019). Restarting Frank-Wolfe. Proceedings of AISTATS.
[PDF]
[arXiv]
[summary]
[slides]
mlopt
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
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
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
Pokutta, S., Singh, M., and Torrico, A. (2018). Efficient algorithms for robust submodular maximization under matroid constraints. ICML Workshop Paper.
[PDF]
[arXiv]
mloptrobopt
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
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
Roy, A., Xu, H., and Pokutta, S. (2017). Reinforcement Learning under Model Mismatch. Proceedings of NIPS.
[arXiv]
mlopt
Braun, G., Pokutta, S., and Zink, D. (2017). Lazifying Conditional Gradient Algorithms. Proceedings of the International Conference on Machine Learning (ICML).
[PDF]
[arXiv]
[slides]
[poster]
mlopt
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
Roy, A., and Pokutta, S. (2016). Hierarchical Clustering via Spreading Metrics. Proceedings of NIPS.
[PDF]
[arXiv]
mlopt
(Oral Presentation + Conference Proceedings)
Braun, G., Roy, A., and Pokutta, S. (2016). Stronger Reductions for Extended Formulations. Proceedings of IPCO.
[arXiv]
extendedformulationipopt
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
Song, R., Xie, Y., and Pokutta, S. (2015). Sequential Sensing with Model Mismatch. Proceedings of ISIT.
mloptsignalprocessing
Braun, G., and Pokutta, S. (2015). The matching polytope does not admit fully-polynomial size relaxation schemes. Proceeedings of SODA.
[arXiv]
extendedformulationipopt
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
Pokutta, S. (2015). Information Theory and Polyhedral Combinatorics. Proceedings of 53rd Annual Allerton Conference on Communication, Control, and Computing.
[PDF]
extendedformulationinformationtheoryipoptsurvey
Xie, Y., Li, Q., and Pokutta, S. (2015). Supervised Online Subspace Tracking. Proceedings of Asilomar Conference on Signals, Systems, and Computers.
mloptsignalprocessing
Braun, G., Pokutta, S., and Zink, D. (2015). Inapproximability of combinatorial problems via small LPs and SDPs. Proceeedings of STOC.
[arXiv]
[video]
extendedformulationipopt
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
Braun, G., Fiorini, S., and Pokutta, S. (2014). Average case polyhedral complexity of the maximum stable set problem. Proceedings of RANDOM.
[PDF]
[arXiv]
extendedformulationipopt
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
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
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
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
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]
extendedformulationipopt
(Best paper award at STOC 2012)
Braun, G., Fiorini, S., Pokutta, S., and Steurer, D. (2012). Approximation Limits of Linear Programs (Beyond Hierarchies). Proceedings of FOCS.
[arXiv]
extendedformulationipopt
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
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
Pokutta, S., and Schmaltz, C. (2011). Optimal Planning under Basel III Regulations. Proceedings of 24th Australasian Finance and Banking Conference.
[arXiv]
financeopt
Helmke, H., Gluchshenko, O., Martin, A., Peter, A., Pokutta, S., and Siebert, U. (2011). Optimal Mixed-Mode Runway Scheduling. Proceedings of DACS.
[arXiv]
ipopttranslog
Braun, G., and Pokutta, S. (2010). Rank of random half-integral polytopes. Electronic Notes in Discrete Mathematics, 36, 415–422.
[PDF]
[arXiv]
ipoptprobability
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
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
Drewes, S., and Pokutta, S. (2010). Geometric mean maximization in the presence of discrete decisions. Proceedings of 23rd Australasian Finance and Banking Conference.
financeipopt
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
Pokutta, S., and Schmaltz, C. (2009). Optimal degree of centralization of liquidity management. Proceedings of 22nd Australasian Finance and Banking Conference.
[arXiv]
financeopt