A-SDLM: an asynchronous Stochastic Learning Algorithm for fast distributed learning
We propose an asynchronous version of stochastic secondorder optimization algorithm for parallel distributed learning. Our proposed algorithm, namely Asynchronous Stochastic Diagonal Levenberg-Marquardt (A-SDLM) contains only a single hyper-parameter (i.e. the learning rate) while still retaining it...
| Main Authors: | , |
|---|---|
| Format: | Conference or Workshop Item |
| Published: |
2015
|
| Subjects: |