Author

Gesualdo Scutari

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Oct 2026

From Mixing to Tearing: Graph Decomposition in Decentralized Optimization via Message Passing

A graph decomposition framework is introduced that uses the network to design the method, not merely execute it, and it jointly determines how agreement is imposed, which variables are optimized jointly (blocks), and which connected subgraphs host the agents solving each block.

Kuang-Yu Ding, Gesualdo Scutari · 0 citations

#machine learning Preprint Oct 2026

From Mixing to Tearing: Graph Decomposition in Decentralized Optimization via Message Passing

We study the minimization of sums of smooth strongly convex functions over undirected graphs, with each function held by one agent and communication restricted to neighbors in the graph. Existing decentralized methods, whether based on gossip or on routing over spanning trees, typically use the network to mix or aggreg...

Kuang-Yu Ding, Gesualdo Scutari · 0 citations