Showing 2025Show all
3 papers · 1 filter
math.OC2025
A Parameter-free Decentralized Algorithm for Composite Convex Optimization
Xiaokai Chen, Ilya Kuruzov, Gesualdo Scutari +1
The paper studies decentralized optimization over networks, where agents minimize a composite objective consisting of the sum of smooth convex functions--the agents' losses--and an…
math.OC2025
Adaptive Stepsize Selection in Decentralized Convex Optimization
Ilya Kuruzov, Xiaokai Chen, Gesualdo Scutari +1
We study decentralized optimization where multiple agents minimize the average of their (strongly) convex, smooth losses over a communication graph. Convergence of the existing dec…
math.OC2025
DCatalyst: A Unified Accelerated Framework for Decentralized Optimization
Tianyu Cao, Xiaokai Chen, Gesualdo Scutari
We study decentralized optimization over a network of agents, modeled as graphs, with no central server. The goal is to minimize , where represents a (strongly) convex fun…