ivutils
Loading...
Searching...
No Matches
base_optimizer Class Reference

Base optimizer class. More...

#include <gradopt.h>

Inheritance diagram for base_optimizer:

Public Member Functions

virtual int SetAccuracy (double max_df=-1, double max_dx=-1, int max_convit=2, double max_grad=-1)
 Set convergence creiteria:
max_df – maximal function variance at convergence OR;
maximal position variance at convergence, dx is normalized by total variable number OR
maximal gradient norm max_grad at convergence.
 

Detailed Description

Base optimizer class.

Member Function Documentation

◆ SetAccuracy()

virtual int base_optimizer::SetAccuracy ( double  max_df = -1,
double  max_dx = -1,
int  max_convit = 2,
double  max_grad = -1 
)
inlinevirtual

Set convergence creiteria:
max_df – maximal function variance at convergence OR;
maximal position variance at convergence, dx is normalized by total variable number OR
maximal gradient norm max_grad at convergence.


Negative parameters mean that the corresponding criteria are not checked. These conditions have to be repeated for at least max_convit consecutive iterations.

Reimplemented in md_grad_optimizer< term_t >.


The documentation for this class was generated from the following file: