iFedDR: Auto-Tuning Local Computation with Inexact Douglas-Rachford Splitting in Federated Learning

T Pethick, P Latafat, B Lewandowski, Z Xu, P Kairouz… - openreview.net
Federated learning usually requires specifying the amount of local computation needed a
priori. In this work, we instead propose a systematic scheme to automatically adjust and …

On the convergence of warped proximal iterations for solving nonmonotone inclusions and applications

D Papadimitriou, BC Vu - OPT 2023: Optimization for Machine Learning - openreview.net
In machine learning, tackling fairness, robustness, and safeness requires to solve
nonconvex optimization problems with various constraints. In this paper, we investigate the …