Decentralized SGD under Heavy-Tailed Noise: Optimal Convergence Rates and the Role of Gradient Clipping
Clipped decentralized SGD reaches order-optimal rates under heavy-tailed noise with linear agent speed-up.
Stories per day · 30 days
2 stories, newest first · one card per story
Stories tagged #non-convex
CTP-FL: Common-Trajectory Gradient Prediction for Federated Learning
CTP-FL estimates a shared global gradient path at the same per-round cost as FedAvg-M.