3 papers
cs.LG2026
A Multi-Token Coordinate Descent Method for Semi-Decentralized Vertical Federated Learning
Pedro Valdeira, Yuejie Chi, Cláudia Soares +1
Most federated learning (FL) methods use a client-server scheme, where clients communicate only with a central server. However, this scheme is prone to bandwidth bottlenecks at the…
cs.LG2026
CLASP: An online learning algorithm for Convex Losses And Squared Penalties
Ricardo N. Ferreira, João Xavier, Cláudia Soares
We study Constrained Online Convex Optimization (COCO), where a learner chooses actions iteratively, observes both unanticipated convex loss and convex constraint, and accumulates…
cs.LG2025
Communication-efficient Vertical Federated Learning via Compressed Error Feedback
Pedro Valdeira, João Xavier, Cláudia Soares +1
Communication overhead is a known bottleneck in federated learning (FL). To address this, lossy compression is commonly used on the information communicated between the server and…