AINeutralarXiv – CS AI · 7h ago6/10
🧠
Quantized Stochastic Primal-Dual Methods for Distributed Optimization under Relaxed Global Geometry
Researchers propose q-PDGD, a quantized stochastic primal-dual optimization method for distributed systems with limited communication bandwidth. The approach achieves linear convergence under relaxed geometric conditions and matches centralized stochastic optimization rates while reducing communication overhead through quantization.