RandomDescent Class Reference

Random descent policy for Stochastic Coordinate Descent(SCD). More...

Static Public Member Functions
template < typename ResolvableFunctionType >
static size_t	DescentFeature (const size_t, const arma::mat &, const ResolvableFunctionType &function)
	The DescentFeature method is used to get the descent coordinate for the current iteration of the SCD optimizer. More...

Detailed Description

Random descent policy for Stochastic Coordinate Descent(SCD).

This descent scheme picks a the co-ordinate for the descent uniformly randomly.

For more information, see the following.

@inproceedings{ShalevShwartz2009,
  author    = {Shalev-Shwartz, Shai and Tewari, Ambuj},
  title     = {Stochastic Methods for L1 Regularized Loss Minimization},
  booktitle = {Proceedings of the 26th Annual International Conference on
               Machine Learning},
  series    = {ICML '09},
  year      = {2009},
  isbn      = {978-1-60558-516-1}
}

Definition at line 37 of file random_descent.hpp.

Member Function Documentation

DescentFeature()

static size_t DescentFeature ( const size_t  , const arma::mat &  , const ResolvableFunctionType &  function  )

inlinestatic

The DescentFeature method is used to get the descent coordinate for the current iteration of the SCD optimizer.

For more information regarding the interface of this policy with the optimizer, have a look at the SCD implementation.

Template Parameters

ResolvableFunctionType

The type of the function to be optimized.

Parameters

iteration	The iteration number for which the feature is to be obtained.
iterate	The current value of the decision variable.
function	The function to be optimized.

Returns

The index of the coordinate to be descended.

Definition at line 54 of file random_descent.hpp.

References mlpack::math::RandInt().

---

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

• src/mlpack/core/optimizers/scd/descent_policies/random_descent.hpp