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.
1 stories, newest first · one card per story
Clipped decentralized SGD reaches order-optimal rates under heavy-tailed noise with linear agent speed-up.
Today 1.5K readers · 2.4K views · 757 reads · all time 189K views