Abstract | ||
---|---|---|
We consider centralized and distributed mirror descent (MD) algorithms over a finite-dimensional Hilbert space, and prove that the problem variables converge to an optimizer of a possibly nonsmooth function when the step sizes are square summable but not summable. Prior literature has focused on the convergence of the function value to its optimum. However, applications from distributed optimizati... |
Year | DOI | Venue |
---|---|---|
2019 | 10.1109/LCSYS.2018.2854889 | IEEE Control Systems Letters |
Keywords | Field | DocType |
Convergence,Mirrors,Games,Optimization,Linear programming,Hilbert space,Standards | Convergence (routing),Hilbert space,Mathematical optimization,Convexity,Subgradient method,Robust regression,Iterated function,Mathematics | Journal |
Volume | Issue | ISSN |
3 | 1 | 2475-1456 |
Citations | PageRank | References |
1 | 0.35 | 15 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Thinh Thanh Doan | 1 | 10 | 4.90 |
Subhonmesh Bose | 2 | 10 | 3.82 |
Dinh Hoa Nguyen | 3 | 56 | 9.05 |
Carolyn L. Beck | 4 | 401 | 60.19 |