SOURCE-LINKED INTELLIGENCE

Federated stochastic bilevel optimization with fully first-order gradients

arXiv · AI, language, vision and robotics · article · Sep 14, 2026 · UTC

Federated stochastic bilevel optimization has been actively studied in recent years due to its widespread applications in machine learning. However, most existing federated stochastic bilevel optimization algorithms require the computation of second-order Hessian and Jacobian matrices, which leads to longer running times in practice. To address these challenges, we propose a novel federated stochastic variance-reduced bilevel gradient descent algorithm that relies solely on first-order oracles. Specifically, our approach does not require the computation of second-order Hessian and Jacobian mat

Read original source ↗ Open in workspace

recordType

paper

region

Global