Federated learning
In the sense of being privacy-preserving pooled learning
2023-10-13 — 2024-09-30
Wherein the collaborative training of models across distributed devices is described by an inferential framework, and the effects of local sampling variability on central aggregation are examined.
agents
bounded compute
collective knowledge
distributed
economics
edge computing
game theory
incentive mechanisms
machine learning
networks
Placeholder.
1 References
Sadeghi, Wang, Ma, et al. 2020. “Learning While Respecting Privacy and Robustness to Distributional Uncertainties and Adversarial Data.” arXiv:2007.03724 [Cs, Eess, Math].