Federated learning with PyTorch (federated averaging and consensus optimization): with 'reduced' bandwidth

Numerical illustration of a novel analysis framework for consensus-based optimization (CBO) and numerical experiments demonstrating the practicability of the method

SAGECal is a fast, memory efficient and GPU accelerated radio interferometric calibration program. It supports all source models including points, Gaussians and Shapelets. Distributed calibration using MPI and consensus optimization is enabled. Both spectral and spatial priors can be used as constraints. Tools to build/restore sky models are inc…

hReg-CNCC is a high-quality Regulatory network of Cranial Neural Crest Cell (CNCC), built by consensus optimization.

A consensus-based optimization methods for saddle point problems (CBO-SP)

Code for numerical results in the ICASSP 2020 paper "Decentralized optimization with non-identical sampling in presence of stragglers".