BacktrackingLineSearch Class Reference

Definition of the backtracking line search algorithm based on the Armijo–Goldstein condition to determine the maximum amount to move along the given search direction. More...

Public Member Functions
	BacktrackingLineSearch (const double searchParameter=0.1)
	Construct the BacktrackingLineSearch object with the given function and parameters. More...
template < typename DecomposableFunctionType >
void	Update (DecomposableFunctionType &function, double &stepSize, arma::mat &iterate, const arma::mat &gradient, const double gradientNorm, const double, const size_t offset, const size_t, const size_t backtrackingBatchSize, const bool reset)
	This function is called in each iteration. More...

Detailed Description

Definition of the backtracking line search algorithm based on the Armijo–Goldstein condition to determine the maximum amount to move along the given search direction.

For more information, please refer to:

@article{De2017,
  title   = {Big Batch {SGD:} Automated Inference using Adaptive Batch
             Sizes},
  author  = {Soham De and Abhay Kumar Yadav and David W. Jacobs and
             Tom Goldstein},
  journal = {CoRR},
  year    = {2017},
  url     = {http://arxiv.org/abs/1610.05792},
}

Definition at line 40 of file backtracking_line_search.hpp.

Constructor & Destructor Documentation

BacktrackingLineSearch()

BacktrackingLineSearch ( const double  searchParameter = 0.1 )

inline

Construct the BacktrackingLineSearch object with the given function and parameters.

The defaults here are not necessarily good for the given problem, so it is suggested that the values used be tailored to the task at hand.

Parameters

function

Function to be optimized (minimized).

Definition at line 51 of file backtracking_line_search.hpp.

Member Function Documentation

Update()

void Update ( DecomposableFunctionType &  function, double &  stepSize, arma::mat &  iterate, const arma::mat &  gradient, const double  gradientNorm, const double  , const size_t  offset, const size_t  , const size_t  backtrackingBatchSize, const bool  reset  )

inline

This function is called in each iteration.

Template Parameters

DecomposableFunctionType

Type of the function to be optimized.

Parameters

function	Function to be optimized (minimized).
stepSize	Step size to be used for the given iteration.
iterate	Parameters that minimize the function.
gradient	The gradient matrix.
gradientNorm	The gradient norm to be used for the given iteration.
offset	The batch offset to be used for the given iteration.
batchSize	Batch size to be used for the given iteration.
backtrackingBatchSize	Backtracking batch size to be used for the given iteration.
reset	Reset the step size decay parameter.

Definition at line 71 of file backtracking_line_search.hpp.

---

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

• src/mlpack/core/optimizers/bigbatch_sgd/backtracking_line_search.hpp