3 papers
cs.LG2025
Cross-Learning from Scarce Data via Multi-Task Constrained Optimization
Leopoldo Agorio, Juan Cerviño, Miguel Calvo-Fullana +2
A learning task, understood as the problem of fitting a parametric model from supervised data, fundamentally requires the dataset to be large enough to be representative of the und…
eess.SY2025
Cooperative Multi-Agent Assignment over Stochastic Graphs via Constrained Reinforcement Learning
Leopoldo Agorio, Sean Van Alen, Santiago Paternain +2
Constrained multi-agent reinforcement learning offers the framework to design scalable and almost surely feasible solutions for teams of agents operating in dynamic environments to…
cs.LG2024
Convolutional Filtering with RKHS Algebras
Alejandro Parada-Mayorga, Leopoldo Agorio, Alejandro Ribeiro +1
In this paper, we develop a generalized theory of convolutional signal processing and neural networks for Reproducing Kernel Hilbert Spaces (RKHS). Leveraging the theory of algebra…