Fast and Efficient Asynchronous Gossip Algorithm for Robust and Non-Smooth Convex Decentralized Learning.

arXiv:2601.20571v3 Announce Type: replace-cross Abstract: Asynchronous primal-dual methods for decentralized non-smooth convex optimization often require each node to maintain $\mathcal{O}(d)$ auxiliary variables, where $d$ is its degree. This dependence on de