Almanac
technique

Multi-Gossip Accelerated DSGD

techniqueactiveprovisionalmulti-gossip-accelerated-dsgd-adb67da1·1 events·first seen 9d ago

Aliases: Multi-Gossip Accelerated DSGD

Co-occurring entities

More like this (12)

Recent events (1)

4arXiv · cs.LG·9d ago·source ↗

MG-ADSGD achieves optimal communication complexity for decentralized stochastic strongly convex optimization

Researchers propose Multi-Gossip Accelerated DSGD (MG-ADSGD), a decentralized stochastic optimization algorithm that simultaneously achieves accelerated dependence on both the condition number (√κ) and the network spectral gap (1/√(1-β)), a combination no prior stochastic method had attained. The algorithm couples gossip depth with mini-batch size so that additional communication rounds improve both consensus accuracy and gradient variance reduction. The resulting communication complexity is claimed to be the best currently known for decentralized stochastic strongly convex optimization up to logarithmic factors.