FEDFW provably finds an ε-suboptimal solution of the constrained empirical risk-minimization problem after O(ε−2) iterations if the objective function is convex. The rate becomes O(ε−3) if the objective is non- convex. The method enjoys data privacy, low per-iteration cost and communication of sparse signals.
Aug 19, 2024 · We propose a Federated Frank-Wolfe Algorithm (FedFW). FedFW features data privacy, low per-iteration cost, and communication of sparse signals.
Oct 20, 2022 · This paper introduces the Federated Frank-Wolfe algorithm for solving constrained optimization problem in distributed regime. Authors provided ...
Aug 22, 2024 · We propose a Federated Frank-Wolfe Algorithm (FedFW). FedFW features data privacy, low per-iteration cost, and communication of sparse signals.
People also ask
What is the Frank Wolfe algorithm?
What is federated learning algorithm?
What is the federated learning averaging algorithm?
What is the difference between Frank Wolfe and gradient descent?
Sep 8, 2024 · We propose a Federated Frank-Wolfe Algorithm (FedFW). FedFW features data privacy, low per-iteration cost, and communication of sparse signals.
We propose a Federated Frank-Wolfe Algorithm (FedFW). FedFW features data privacy, low per-iteration cost, and communication of sparse signals.
Feb 23, 2023 · We demonstrate empirical performance of the FedFW algorithm on several machine learning tasks. Place, publisher, year, edition, pages. 2022.
A general decentralized algorithm can be traced back to (Nedic and Ozdaglar 2009) that combines gradient descent method and Gossip-type consensus step.
In this paper, we propose DP-FedFW, a novel Frank-Wolfe based federated learning algorithm with local (ϵ,δ)-differential privacy (DP) guarantees in a ...
Aug 22, 2024 · Federated learning (FL) has gained a lot of attention in recent years for building privacy-preserving collaborative learning systems.