SOURCE-LINKED INTELLIGENCE

Beyond Conventional Federated Learning via High-Order Regularization

arXiv · AI, language, vision and robotics · article · Sep 9, 2026 · UTC

Federated clients that perform several local optimization steps can return parameter displacements with widely different magnitudes. The quadratic regularization of FedProx grows linearly with displacement and therefore offers limited control over the contrast between ordinary and unusually large client movements. We here introduce HiFedProx, which replaces the quadratic penalty with a scale-matched power-type regularizer indexed by $p\geq2$. All powers have the same regularization-gradient magnitude at a reference displacement $R$, while every $p>2$ gives a weaker response below $R$ and a str

Read original source ↗ Open in workspace

recordType

paper

region

Global