mlpack
gitmaster

VanillaUpdate Class Reference
Vanilla update policy for Stochastic Gradient Descent (SGD). More...
Public Member Functions  
void  Initialize (const size_t, const size_t) 
The Initialize method is called by SGD Optimizer method before the start of the iteration update process. More...  
void  Update (arma::mat &iterate, const double stepSize, const arma::mat &gradient) 
Update step for SGD. More...  
Detailed Description
Vanilla update policy for Stochastic Gradient Descent (SGD).
The following update scheme is used to update SGD in every iteration:
where is a parameter which specifies the step size. is chosen according to (the iteration number).
Definition at line 31 of file vanilla_update.hpp.
Member Function Documentation
◆ Initialize()

inline 
The Initialize method is called by SGD Optimizer method before the start of the iteration update process.
The vanilla update doesn't initialize anything.
 Parameters

rows Number of rows in the gradient matrix. cols Number of columns in the gradient matrix.
Definition at line 42 of file vanilla_update.hpp.
◆ Update()

inline 
Update step for SGD.
The function parameters are updated in the negative direction of the gradient.
 Parameters

iterate Parameters that minimize the function. stepSize Step size to be used for the given iteration. gradient The gradient matrix.
Definition at line 53 of file vanilla_update.hpp.
The documentation for this class was generated from the following file:
 src/mlpack/core/optimizers/sgd/update_policies/vanilla_update.hpp
Generated by 1.8.13