4 papers
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…
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…
Deep-Relative-Trust-Based Diffusion for Decentralized Deep Learning
Muyun Li, Aaron Fainman, Stefan Vlaski
Decentralized learning strategies allow a collection of agents to learn efficiently from local data sets without the need for central aggregation or orchestration. Current decentra…
Decentralized Learning with Approximate Finite-Time Consensus
Aaron Fainman, Stefan Vlaski
The performance of algorithms for decentralized optimization is affected by both the optimization error and the consensus error, the latter of which arises from the variation betwe…