DS FedProxGrad: Asymptotic Stationarity Without Noise Floor in Fair Federated Learning
By: Huzaifa Arif
Recent work \cite{arifgroup} introduced Federated Proximal Gradient \textbf{(\texttt{FedProxGrad})} for solving non-convex composite optimization problems in group fair federated learning. However, the original analysis established convergence only to a \textit{noise-dominated neighborhood of stationarity}, with explicit dependence on a variance-induced noise floor. In this work, we provide an improved asymptotic convergence analysis for a generalized \texttt{FedProxGrad}-type analytical framework with inexact local proximal solutions and explicit fairness regularization. We call this extended analytical framework \textbf{DS \texttt{FedProxGrad}} (Decay Step Size \texttt{FedProxGrad}). Under a Robbins-Monro step-size schedule \cite{robbins1951stochastic} and a mild decay condition on local inexactness, we prove that $\liminf_{r\to\infty} \mathbb{E}[\|\nabla F(\mathbf{x}^r)\|^2] = 0$, i.e., the algorithm is asymptotically stationary and the convergence rate does not depend on a variance-induced noise floor.
Similar Papers
Federated Stochastic Minimax Optimization under Heavy-Tailed Noises
Machine Learning (CS)
Helps computers learn better with messy data.
Sharp Gaussian approximations for Decentralized Federated Learning
Machine Learning (Stat)
Detects computer attacks by watching how they learn.
Operator-Theoretic Framework for Gradient-Free Federated Learning
Machine Learning (CS)
Makes AI learn from private data without sharing it.