FedProx Algorithm

FedProx is a federated learning algorithm designed to address the challenges of training machine learning models on decentralized, heterogeneous data while preserving data privacy. Current research focuses on improving its convergence properties, particularly in non-smooth and non-convex settings, and enhancing its robustness to noisy data and communication constraints, often incorporating techniques like extrapolation and quantization. This work is significant because it contributes to the development of more efficient and privacy-preserving machine learning methods applicable to diverse real-world scenarios, such as those involving Internet of Things devices and medical data.