Mathematical Foundations of Artificial Intelligence Group
Research goals
The research of the Mathematical Foundations of Artificial Intelligence Group focuses on explainable AI, aiming to understand AI algorithms by establishing their mathematical properties. We apply these properties across various research fields, including machine learning and wireless systems.
Key papers
M Gabor, T Piotrowski, RLG Cavalcante Positive Concave Deep Equilibrium Models, In: ICML’24: Proceedings of the 41st International Conference on Machine Learning (2024) pp. 14365-14381.
TJ Piotrowski, RLG Cavalcante, M Gabor, Fixed points of nonnegative neural networks, Journal of Machine Learning Research, 25 (2024), pp. 1-40.
T Piotrowski, R Ismayilov, M Frey, RLG Cavalcante, Inverse Feasibility in Over-the-Air Federated Learning, IEEE Signal Processing Letters, 31 (2024), pp. 1434-1438.
T Piotrowski, RLG Cavalcante, The Fixed Point Iteration of Positive Concave Mappings Converges Geometrically if a Fixed Point Exists: Implications to Wireless Systems, IEEE Transactions on Signal Processing, 70 (2022), pp. 4697-4710.