Showing math.OCShow all
3 papers · 1 filter
math.OC2025
Graph-Aware Learning Rates for Decentralized Optimization
Aaron Fainman, Stefan Vlaski
We propose an adaptive step-size rule for decentralized optimization. Choosing a step-size that balances convergence and stability is challenging. This is amplified in the decentra…
math.OC2025
On the Convergence of Decentralized Stochastic Gradient-Tracking with Finite-Time Consensus
Aaron Fainman, Stefan Vlaski
Algorithms for decentralized optimization and learning rely on local optimization steps coupled with combination steps over a graph. Recent works have demonstrated that using a tim…
math.OC2024
Learned Finite-Time Consensus for Distributed Optimization
Aaron Fainman, Stefan Vlaski
Most algorithms for decentralized learning employ a consensus or diffusion mechanism to drive agents to a common solution of a global optimization problem. Generally this takes the…