Entity · paper

Accelerated Decentralized Stochastic Gradient Descent for Strongly Convex Optimization

paperactiveaccelerated-decentralized-stochastic-gradient-descent-for-strongly-convex-optimization-88670200·1 events·first seen Jun 8, 2026

Aliases: Accelerated Decentralized Stochastic Gradient Descent for Strongly Convex Optimization

Co-occurring entities

Multi-Gossip Accelerated DSGD

More like this (12)

stochastic gradient ascent Private Stochastic Convex Optimization differentiable convex optimization randomized coordinate descent Complexity Bounds and Approaches to Learning Projected Gradient Descent Solver Iterates Gradient-Guided Reward Optimization distributed optimization distributionally robust optimization conjugate gradient Divergence Regularized Policy Optimization Beyond Negative-Ridge Endpoints: Mixed-Sign Spectral Regularization via Negative-Shifted Gradient Descent One-Step Gradient Delay is Not a Barrier for Large-Scale Asynchronous Pipeline Parallel LLM Pretraining

Recent events (1)

4arXiv · cs.LG·Jun 8, 2026·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.

Training Infrastructure Multi-Gossip Accelerated DSGD Accelerated Decentralized Stochastic Gradient Descent for Strongly Convex Optimization