TY - CHAP A1 - Zimmer, Max A1 - Spiegel, Christoph A1 - Pokutta, Sebastian T1 - How I Learned to Stop Worrying and Love Retraining T2 - Proceedings of International Conference on Learning Representations Y1 - 2023 ER - TY - CHAP A1 - Kera, Hiroshi A1 - Pelleriti, Nico A1 - Ishihara, Yuki A1 - Zimmer, Max A1 - Pokutta, Sebastian T1 - Computational Algebra with Attention: Transformer Oracles for Border Basis Algorithms T2 - Proceedings of the Conference on Neural Information Processing Systems Y1 - 2025 ER - TY - CHAP A1 - Fayad, Ibrahim A1 - Zimmer, Max A1 - Schwartz, Martin A1 - Ciais, Philippe A1 - Gieseke, Fabian A1 - Belouze, Gabriel A1 - Brood, Sarah A1 - De Truchis, Aurelien A1 - d'Aspremont, Alexandre T1 - DUNIA: Pixel-Sized Embeddings via Cross-Modal Alignment for Earth Observation Applications T2 - Proceedings of the 42nd International Conference on Machine Learning Y1 - 2025 UR - https://raw.githubusercontent.com/mlresearch/v267/main/assets/fayad25a/fayad25a.pdf VL - 267 SP - 16375 EP - 16406 ER - TY - CHAP A1 - Pauls, Jan A1 - Zimmer, Max A1 - Turan, Berkant A1 - Saatchi, Sassan A1 - Ciais, Philippe A1 - Pokutta, Sebastian A1 - Gieseke, Fabian T1 - Capturing Temporal Dynamics in Large-Scale Canopy Tree Height Estimation T2 - Proceedings of the 42nd International Conference on Machine Learning Y1 - 2025 UR - https://raw.githubusercontent.com/mlresearch/v267/main/assets/pauls25a/pauls25a.pdf VL - 267 SP - 48422 EP - 48438 ER - TY - CHAP A1 - Mundinger, Konrad A1 - Zimmer, Max A1 - Kiem, Aldo A1 - Spiegel, Christoph A1 - Pokutta, Sebastian T1 - Neural Discovery in Mathematics: Do Machines Dream of Colored Planes? T2 - Proceedings of the 42nd International Conference on Machine Learning Y1 - 2025 UR - https://raw.githubusercontent.com/mlresearch/v267/main/assets/mundinger25a/mundinger25a.pdf VL - 267 SP - 45236 EP - 45255 ER - TY - CHAP A1 - Pelleriti, Nico A1 - Zimmer, Max A1 - Wirth, Elias A1 - Pokutta, Sebastian T1 - Approximating Latent Manifolds in Neural Networks via Vanishing Ideals T2 - Proceedings of the 42nd International Conference on Machine Learning Y1 - 2025 UR - https://raw.githubusercontent.com/mlresearch/v267/main/assets/pelleriti25a/pelleriti25a.pdf VL - 267 SP - 48734 EP - 48761 ER - TY - CHAP A1 - Pauls, Jan A1 - Zimmer, Max A1 - Kelly, Una M A1 - Schwartz, Martin A1 - Saatchi, Sassan A1 - Ciais, Philippe A1 - Pokutta, Sebastian A1 - Brandt, Martin A1 - Gieseke, Fabian T1 - Estimating canopy height at scale T2 - Proceedings of the 41st International Conference on Machine Learning N2 - We propose a framework for global-scale canopy height estimation based on satellite data. Our model leverages advanced data preprocessing techniques, resorts to a novel loss function designed to counter geolocation inaccuracies inherent in the ground-truth height measurements, and employs data from the Shuttle Radar Topography Mission to effectively filter out erroneous labels in mountainous regions, enhancing the reliability of our predictions in those areas. A comparison between predictions and ground-truth labels yields an MAE/RMSE of 2.43 / 4.73 (meters) overall and 4.45 / 6.72 (meters) for trees taller than five meters, which depicts a substantial improvement compared to existing global-scale products. The resulting height map as well as the underlying framework will facilitate and enhance ecological analyses at a global scale, including, but not limited to, large-scale forest and biomass monitoring. Y1 - 2024 UR - https://raw.githubusercontent.com/mlresearch/v235/main/assets/pauls24a/pauls24a.pdf VL - 235 SP - 39972 EP - 39988 ER - TY - JOUR A1 - Mundinger, Konrad A1 - Pokutta, Sebastian A1 - Spiegel, Christoph A1 - Zimmer, Max T1 - Extending the Continuum of Six-Colorings JF - Geombinatorics Quarterly Y1 - 2024 VL - 34 IS - 1 SP - 20 EP - 29 ER - TY - CHAP A1 - Mundinger, Konrad A1 - Pokutta, Sebastian A1 - Spiegel, Christoph A1 - Zimmer, Max T1 - Extending the Continuum of Six-Colorings T2 - Discrete Mathematics Days 2024 Y1 - 2024 U6 - https://doi.org/10.37536/TYSP5643 SP - 178 EP - 183 ER - TY - CHAP A1 - Wäldchen, Stephan A1 - Sharma, Kartikey A1 - Turan, Berkant A1 - Zimmer, Max A1 - Pokutta, Sebastian T1 - Interpretability Guarantees with Merlin-Arthur Classifiers T2 - Proceedings of The 27th International Conference on Artificial Intelligence and Statistics N2 - We propose an interactive multi-agent classifier that provides provable interpretability guarantees even for complex agents such as neural networks. These guarantees consist of lower bounds on the mutual information between selected features and the classification decision. Our results are inspired by the Merlin-Arthur protocol from Interactive Proof Systems and express these bounds in terms of measurable metrics such as soundness and completeness. Compared to existing interactive setups, we rely neither on optimal agents nor on the assumption that features are distributed independently. Instead, we use the relative strength of the agents as well as the new concept of Asymmetric Feature Correlation which captures the precise kind of correlations that make interpretability guarantees difficult. We evaluate our results on two small-scale datasets where high mutual information can be verified explicitly. Y1 - 2024 UR - https://proceedings.mlr.press/v238/waldchen24a/waldchen24a.pdf VL - 238 SP - 1963 EP - 1971 ER - TY - CHAP A1 - Zimmer, Max A1 - Spiegel, Christoph A1 - Pokutta, Sebastian T1 - Sparse Model Soups T2 - 12th International Conference on Learning Representations (ICLR 2024) Y1 - 2024 SN - 9781713898658 PB - Curran Associates, Inc. ER - TY - CHAP A1 - Roux, Christophe A1 - Zimmer, Max A1 - Pokutta, Sebastian T1 - On the byzantine-resilience of distillation-based federated learning T2 - 13th International Conference on Learning Representations (ICLR 2025) N2 - Federated Learning (FL) algorithms using Knowledge Distillation (KD) have received increasing attention due to their favorable properties with respect to privacy, non-i.i.d. data and communication cost. These methods depart from transmitting model parameters and instead communicate information about a learning task by sharing predictions on a public dataset. In this work, we study the performance of such approaches in the byzantine setting, where a subset of the clients act in an adversarial manner aiming to disrupt the learning process. We show that KD-based FL algorithms are remarkably resilient and analyze how byzantine clients can influence the learning process. Based on these insights, we introduce two new byzantine attacks and demonstrate their ability to break existing byzantine-resilient methods. Additionally, we propose a novel defence method which enhances the byzantine resilience of KD-based FL algorithms. Finally, we provide a general framework to obfuscate attacks, making them significantly harder to detect, thereby improving their effectiveness. Y1 - 2025 UR - https://openreview.net/pdf?id=of6EuHT7de ER - TY - CHAP A1 - Zimmer, Max A1 - Spiegel, Christoph A1 - Pokutta, Sebastian ED - Fackeldey, K. T1 - Compression-aware training of neural networks using Frank-Wolfe T2 - Mathematical Optimization for Machine Learning: Proceedings of the MATH+ Thematic Einstein Semester 2023 Y1 - 2025 U6 - https://doi.org/10.1515/9783111376776-010 SP - 137 EP - 168 PB - De Gruyter ER - TY - JOUR A1 - Pokutta, Sebastian A1 - Spiegel, Christoph A1 - Zimmer, Max T1 - Deep Neural Network Training with Frank-Wolfe N2 - This paper studies the empirical efficacy and benefits of using projection-free first-order methods in the form of Conditional Gradients, a.k.a. Frank-Wolfe methods, for training Neural Networks with constrained parameters. We draw comparisons both to current state-of-the-art stochastic Gradient Descent methods as well as across different variants of stochastic Conditional Gradients. In particular, we show the general feasibility of training Neural Networks whose parameters are constrained by a convex feasible region using Frank-Wolfe algorithms and compare different stochastic variants. We then show that, by choosing an appropriate region, one can achieve performance exceeding that of unconstrained stochastic Gradient Descent and matching state-of-the-art results relying on L2-regularization. Lastly, we also demonstrate that, besides impacting performance, the particular choice of constraints can have a drastic impact on the learned representations. Y1 - 2020 ER - TY - CHAP A1 - Lasby, Mike A1 - Zimmer, Max A1 - Pokutta, Sebastian A1 - Schultheis, Erik T1 - Compressed sparse tiles for memory-efficient unstructured and semi-structured sparsity T2 - Proceedings of the ICLR Workshop on Sparsity in LLMs Y1 - 2025 UR - https://openreview.net/forum?id=iso0KV2HVq ER -