4 papers · 1 filter
Adaptive Stepsizes With Certified Convergence in Distributed Gradient Tracking With Quadratic Costs
Yifan Wang, Luca Ballotta, Ruggero Carli +3
In this work, we propose an adaptive stepsize rule with guaranteed convergence for Distributed Gradient Tracking applied to scalar quadratic problems with heterogeneous curvatures.…
Timescale Separation Through the Lens of Operator Theory
Guido Carnevale, Nicola Bastianello, Luca Schenato +2
Timescale separation is a powerful tool for analyzing interconnected dynamical systems. Meanwhile, operator theory provides a general framework for studying the convergence of iter…
On Convergence Analysis of Network-GIANT: An approximate Hessian-based fully distributed optimization algorithm
Souvik Das, Luca Schenato, Subhrakanti Dey
This paper presents a detailed convergence and performance analysis of a recently developed approximate Newton-type fully distributed optimization method for \(L\)-smooth, \(μ\)-st…
HBNET-GIANT: A communication-efficient accelerated Newton-type fully distributed optimization algorithm
Souvik Das, Luca Schenato, Subhrakanti Dey
This article presents a second-order fully distributed optimization algorithm, HBNET-GIANT, driven by heavy-ball momentum, for -smooth and -strongly convex objective function…