KrumSimulation¶
KrumSimulation.
- Reference:
Peva Blanchard, El Mahdi El Mhamdi, Rachid Guerraoui, and Julien Stainer. “Machine learning with adversaries: Byzantine tolerant gradient descent.” In Advances in Neural Information Processing Systems 30 (NIPS 2017).
One KrumSimulation instance = one (aggregator, attack, dataset, model)
configuration run over multiple synchronous rounds with no learning rate decay.
- class krum.simulations.centralised.krum_nips_2017.KrumSimulation(*, aggregator_f: int | None = None, **kwargs: Any)[source]¶
Bases:
CentralisedSimulationDistributed SGD simulation.
Compared to the ICML 2018
HiddenVulnerabilitySimulation, this variant:Uses a fixed learning rate (no scheduler;
lr_decay=None, the default inherited fromCentralisedSimulation).Reports misclassification error and cross-entropy loss on the test set.
See also
For the base class, see CentralisedSimulation. For the ICML 2018 counterpart, see HiddenVulnerabilitySimulation.