OCLGMAMLJul 7, 2020

A Distributed Cubic-Regularized Newton Method for Smooth Convex Optimization over Networks

arXiv:2007.03562v1
Originality Incremental advance
AI Analysis

This addresses efficient federated learning over arbitrary network topologies, though it appears incremental as it builds on existing cubic-regularized Newton methods.

The authors tackled distributed convex optimization over networks by proposing a cubic-regularized Newton method that requires only local computations and communications, achieving an O(k^{-3}) convergence rate for functions with Lipschitz gradient and Hessian.

We propose a distributed, cubic-regularized Newton method for large-scale convex optimization over networks. The proposed method requires only local computations and communications and is suitable for federated learning applications over arbitrary network topologies. We show a $O(k^{{-}3})$ convergence rate when the cost function is convex with Lipschitz gradient and Hessian, with $k$ being the number of iterations. We further provide network-dependent bounds for the communication required in each step of the algorithm. We provide numerical experiments that validate our theoretical results.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes