NelderMead Class Reference

Nealder-Mead algorithm for finding suitable hyperparameters. More...

List of all members.

Static Public Member Functions

static double FindMinimum (string evaluation_measure, IList< string > hp_names, IList< DenseVector > initial_hp_values, RatingPredictor recommender, ISplit< IRatings > split)
 Find the the parameters resulting in the minimal results for a given evaluation measure.
static double FindMinimum (string error_measure, RatingPredictor recommender)
 Find best hyperparameter (according to an error measure) using Nelder-Mead search.

Detailed Description

Nealder-Mead algorithm for finding suitable hyperparameters.


Member Function Documentation

static double FindMinimum ( string  evaluation_measure,
IList< string >  hp_names,
IList< DenseVector >  initial_hp_values,
RatingPredictor  recommender,
ISplit< IRatings split 
) [inline, static]

Find the the parameters resulting in the minimal results for a given evaluation measure.

The recommender will be set to the best parameter value after calling this method.

Parameters:
evaluation_measure the name of the evaluation measure
hp_names the names of the hyperparameters to optimize
initial_hp_values the values of the hyperparameters to try out first
recommender the recommender
split the dataset split to use
Returns:
the best (lowest) average value for the hyperparameter
static double FindMinimum ( string  error_measure,
RatingPredictor  recommender 
) [inline, static]

Find best hyperparameter (according to an error measure) using Nelder-Mead search.

Parameters:
error_measure an error measure (lower is better)
recommender a rating predictor (will be set to best hyperparameter combination)
Returns:
the estimated error of the best hyperparameter combination

The documentation for this class was generated from the following file:
Generated on Thu Apr 5 01:11:32 2012 for MyMediaLite by  doxygen 1.6.3