[mlpack-git] [mlpack/mlpack] parallel sgd (#603)

[ranjan]

> +  {
> +    it=1; 
> +    while(it!=maxIterations && halt != true)
> +    {
> +      it++;
> +
> +      int th_num=omp_get_thread_num(); //thread number is stored in which the thread is running. 
> +      arma::mat gradient(iterate.n_rows, iterate.n_cols);  //To make gradient private to each thread it is declared here.
> +      int selectedFunction;
> +    
> +      selectedFunction=std::rand()%numFunctions;
> +      function.Gradient(tIterate[th_num],selectedFunction, gradient);
> +      tIterate[th_num] -= stepSize * gradient;
> +      
> +      
> +      //checking whether or not it will go for tollerence checking 

T is added to run each thread independently T iteration to increase speedup.
Here I have Taken T  as constant(1000).
T can be a function of maxiteration, number of thread,  current  value of  iteration. 

---
You are receiving this because you are subscribed to this thread.
Reply to this email directly or view it on GitHub:
https://github.com/mlpack/mlpack/pull/603/files/a981f8322e84ec06a349b80d261639a282f4f7c5#r58895238
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://mailman.cc.gatech.edu/pipermail/mlpack-git/attachments/20160407/ecd7d9b3/attachment.html>