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

Abstract

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.

22 pages, 2 figures. Preprint, under review

References in corpus (4)

• Peer-to-peer Federated Learning on Graphs
• Second-Order Methods with Cubic Regularization Under Inexact Information
• A Unified Scheme to Accelerate Adaptive Cubic Regularization and Gradient Methods for Convex Optimization
• Inexact Proximal Cubic Regularized Newton Methods for Convex Optimization

Cited by in corpus (1)

• Distributed Newton-like Algorithms and Learning for Optimized Power Dispatch