Decentralized asynchronous optimization with DADAO allows decoupling and acceleration
This work proposes an algorithm that seems to be the first decentralized, accelerated, asynchronous, first-order method for minimizing a sum of \(L\)-smooth and \(\mu\)-strongly convex functions distributed over a network of size \(n\), that unifies several recent approaches. Technical results on \(\epsilon\)-precision reveal very competitive theoretical speed guarantees of the proposed method, that outperforms the state-of-the-art algorithms in the field. Moreover, an SDP relaxation is proposed for deriving the gossip rate of each edge, minimizing the total number of communications for a given graph. Some numerical results and direct comparisons illustrate the theoretical gains of the paper.
- Achieving Geometric Convergence for Distributed Optimization Over Time-Varying Graphs
- An Optimal Algorithm for Decentralized Finite-Sum Optimization
- CVXPY: a Python-embedded modeling language for convex optimization
- Distributed average consensus with least-mean-square deviation
- Effective graph resistance
- Expander graphs in pure and applied mathematics
- EXTRA: an exact first-order algorithm for decentralized consensus optimization
- Fastest Mixing Markov Chain on a Graph
- scientific article; zbMATH DE number 5454133 (Why is no real title available?)
- scientific article; zbMATH DE number 3438157 (Why is no real title available?)
- Minimizing Effective Resistance of a Graph
- Networks, crowds and markets. Reasoning about a highly connected world.
- Recent theoretical advances in decentralized distributed convex optimization
- Scikit-learn: machine learning in Python
- The electrical resistance of a graph captures its commute and cover times
- The error-feedback framework: SGD with delayed gradients
This page was built for publication: Decentralized asynchronous optimization with DADAO allows decoupling and acceleration
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q7308313)
