Why random reshuffling beats stochastic gradient descent

Why random reshuffling beats stochastic gradient descent

Abstract We analyze the convergence rate of the random reshuffling (RR) method, which is a randomized first-order incremental algorithm for minimizing a finite sum of convex component functions. RR proceeds in cycles, picking a uniformly random order (permutation) and processing the c...

Full description

Bibliographic Details
Main Authors: Gürbüzbalaban, M., Ozdaglar, A., Parrilo, P. A
Other Authors: Massachusetts Institute of Technology. Laboratory for Information and Decision Systems
Format: Article
Language:English
Published: Springer Berlin Heidelberg 2021
Online Access:https://hdl.handle.net/1721.1/132030

Internet

https://hdl.handle.net/1721.1/132030

Similar Items