Hi,
In have a question about the HPX smart executors talked about in this article
https://arxiv.org/pdf/1711.01519.pdf . I'm not sure to understand the  
way the way the data is generated. As an example, let's say I want to  
optimize a matrix multiplication task. The executor will use a  
logistic regression to optimize the task but has the logistic  
regression already been trained with previous data from a large data  
set? Or does the executor generate data from the task I give it and  
then it trains a logistic regression using that data which would mean  
that the regression is perfectly optimized for the given task but take  
some time to train.
Thank you very much,


_______________________________________________
hpx-users mailing list
[email protected]
https://mail.cct.lsu.edu/mailman/listinfo/hpx-users

Reply via email to