An inexact subsampled proximal Newton-type method for large-scale machine learning

arXiv: Learning, Volume abs/1708.08552, 2017.

Cited by: 7|Bibtex|Views15|Links
EI

Abstract:

We propose a fast proximal Newton-type algorithm for minimizing regularized finite sums that returns an $epsilon$-suboptimal point in $tilde{mathcal{O}}(d(n + sqrt{kappa d})log(frac{1}{epsilon}))$ FLOPS, where $n$ is number of samples, $d$ is feature dimension, and $kappa$ is the condition number. As long as $n u003e d$, the proposed meth...More

Code:

Data:

Your rating :
0

 

Tags
Comments