Abstract | ||
---|---|---|
We propose mS2GD: a method incorporating a mini-batching scheme for improving the theoretical complexity and practical performance of semi-stochastic gradient descent (S2GD). We consider the problem of minimizing a strongly convex function represented as the sum of an average of a large number of smooth convex functions, and a simple nonsmooth convex regularizer. Our method first performs a determ... |
Year | DOI | Venue |
---|---|---|
2016 | 10.1109/JSTSP.2015.2505682 | IEEE Journal of Selected Topics in Signal Processing |
Keywords | Field | DocType |
Radio frequency,Complexity theory,Signal processing algorithms,Linear systems,Stochastic processes,Indexes,Optimization | Mathematical optimization,Gradient descent,Stochastic gradient descent,Linear system,Computer science,Stochastic process,Random coordinate descent,Convex function,Convex optimization,Speedup | Journal |
Volume | Issue | ISSN |
10 | 2 | 1932-4553 |
Citations | PageRank | References |
34 | 1.13 | 29 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jakub Konecný | 1 | 363 | 19.21 |
Jie Liu | 2 | 61 | 3.25 |
Peter Richtárik | 3 | 1314 | 84.53 |
Martin Takác | 4 | 752 | 49.49 |