Skip to content

directorscut82/Doubly_Stochastic_Gradients

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

38 Commits
 
 
 
 
 
 
 
 

Repository files navigation

Doubly_Stochastic_Gradients

Code for doubly stochastic gradients

This repository contains two implementations of Doubly Stochastic Gradients for large-scale kernel methods [1].

The first one is Matlab code on MNIST 8M dataset.

The second one is a GPU implementation based on the cuda-convnet package [2].

Reference

[1] Bo Dai, Bo Xie, Niao He, Yingyu Liang, Anant Raj, Maria-Florina Balcan, and Le Song. Scalable Kernel Methods via Doubly Stochastic Gradients. arXiv:1407.5599: http://arxiv.org/abs/1407.5599

[2] http://code.google.com/p/cuda-convnet

About

Code for doubly stochastic gradients

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Cuda 77.8%
  • Python 15.2%
  • C++ 4.6%
  • Makefile 1.5%
  • Other 0.9%