Open oneway3124 opened 3 years ago
@oneway3124 , the operations involved in the problem are very computationally expensive. And for each appliance each of those operations need to be executed. Hence, it is taking more time for training. How is the performance when a smaller dataset is used?
This convergence problem has been fixed by me. Maybe your argmin error representation is wrong.
For optimization problem, it is trustworthy that the optimization procedure should be completed ASAP. But DSC algorithm cannot convergence before the arrival of the maximal times. Why?