Masaki Uchihara

Quantum Federated Learning Based on Bures--Uhlmann Geometry for Heterogeneous Noisy Clients

This work employs the Bures metric as a local preconditioner and uses the mean Uhlmann curvature to develop an achievable-precision aggregation rule that dynamically down-weights unreliable clients and establishes theoretical guarantees by proving a convergence theorem and a variance-dominance proposition.