Factor graph optimization problems can be lifted via Shor's relaxation and Burer-Monteiro factorization to produce certifiable estimators that preserve the original factor graph connectivity and can be implemented with existing libraries.
Boumal,An introduction to optimization on smooth manifolds
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
FedSPDnet uses manifold projections and retractions to average Stiefel-constrained parameters in federated SPDnet, outperforming standard federated EEGnet on EEG motor imagery benchmarks in F1 score and robustness.
citing papers explorer
-
Certifiable Factor Graph Optimization
Factor graph optimization problems can be lifted via Shor's relaxation and Burer-Monteiro factorization to produce certifiable estimators that preserve the original factor graph connectivity and can be implemented with existing libraries.
-
FedSPDnet: Geometry-Aware Federated Deep Learning with SPDnet
FedSPDnet uses manifold projections and retractions to average Stiefel-constrained parameters in federated SPDnet, outperforming standard federated EEGnet on EEG motor imagery benchmarks in F1 score and robustness.