Showing 2025Show all
3 papers · 1 filter
math.OC2025
AdGT: Decentralized Gradient Tracking with Adaptive Per-Agent Stepsizes
Diyako Ghaderyan, Stefan Werner
In decentralized optimization, gradient-tracking methods typically rely on a single global stepsize. This choice can be conservative when agents have local objectives with differen…
cs.LG2025
Federated Smoothing ADMM for Localization
Reza Mirzaeifard, Ashkan Moradi, Masahiro Yukawa +1
This paper addresses the challenge of localization in federated settings, which are characterized by distributed data, non-convexity, and non-smoothness. To tackle the scalability…
cs.LG2025
Smoothing ADMM for Non-convex and Non-smooth Hierarchical Federated Learning
Reza Mirzaeifard, Stefan Werner
This paper presents a hierarchical federated learning (FL) framework that extends the alternating direction method of multipliers (ADMM) with smoothing techniques, tailored for non…