mlpack
git-master
|
RMSProp is an optimizer that utilizes the magnitude of recent gradients to normalize the gradients. More...
Public Member Functions | |
RMSProp (const double stepSize=0.01, const size_t batchSize=32, const double alpha=0.99, const double epsilon=1e-8, const size_t maxIterations=100000, const double tolerance=1e-5, const bool shuffle=true) | |
Construct the RMSProp optimizer with the given function and parameters. More... | |
double | Alpha () const |
Get the smoothing parameter. More... | |
double & | Alpha () |
Modify the smoothing parameter. More... | |
size_t | BatchSize () const |
Get the batch size. More... | |
size_t & | BatchSize () |
Modify the batch size. More... | |
double | Epsilon () const |
Get the value used to initialise the mean squared gradient parameter. More... | |
double & | Epsilon () |
Modify the value used to initialise the mean squared gradient parameter. More... | |
size_t | MaxIterations () const |
Get the maximum number of iterations (0 indicates no limit). More... | |
size_t & | MaxIterations () |
Modify the maximum number of iterations (0 indicates no limit). More... | |
template < typename DecomposableFunctionType > | |
double | Optimize (DecomposableFunctionType &function, arma::mat &iterate) |
Optimize the given function using RMSProp. More... | |
bool | Shuffle () const |
Get whether or not the individual functions are shuffled. More... | |
bool & | Shuffle () |
Modify whether or not the individual functions are shuffled. More... | |
double | StepSize () const |
Get the step size. More... | |
double & | StepSize () |
Modify the step size. More... | |
double | Tolerance () const |
Get the tolerance for termination. More... | |
double & | Tolerance () |
Modify the tolerance for termination. More... | |
Detailed Description
RMSProp is an optimizer that utilizes the magnitude of recent gradients to normalize the gradients.
In its basic form, given a step rate and a decay term
we perform the following updates:
For more information, see the following.
For RMSProp to work, a DecomposableFunctionType template parameter is required. This class must implement the following function:
size_t NumFunctions(); double Evaluate(const arma::mat& coordinates, const size_t i, const size_t batchSize); void Gradient(const arma::mat& coordinates, const size_t i, arma::mat& gradient, const size_t batchSize);
NumFunctions() should return the number of functions ( ), and in the other two functions, the parameter i refers to which individual function (or gradient) is being evaluated. So, for the case of a data-dependent function, such as NCA (see mlpack::nca::NCA), NumFunctions() should return the number of points in the dataset, and Evaluate(coordinates, 0) will evaluate the objective function on the first point in the dataset (presumably, the dataset is held internally in the DecomposableFunctionType).
Definition at line 67 of file rmsprop.hpp.
Constructor & Destructor Documentation
◆ RMSProp()
RMSProp | ( | const double | stepSize = 0.01 , |
const size_t | batchSize = 32 , |
||
const double | alpha = 0.99 , |
||
const double | epsilon = 1e-8 , |
||
const size_t | maxIterations = 100000 , |
||
const double | tolerance = 1e-5 , |
||
const bool | shuffle = true |
||
) |
Construct the RMSProp optimizer 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. The maximum number of iterations refers to the maximum number of points that are processed (i.e., one iteration equals one point; one iteration does not equal one pass over the dataset).
- Parameters
-
stepSize Step size for each iteration. batchSize Number of points to process in each step. alpha Smoothing constant, similar to that used in AdaDelta and momentum methods. epsilon Value used to initialise the mean squared gradient parameter. maxIterations Maximum number of iterations allowed (0 means no limit). tolerance Maximum absolute tolerance to terminate algorithm. shuffle If true, the function order is shuffled; otherwise, each function is visited in linear order.
Member Function Documentation
◆ Alpha() [1/2]
|
inline |
Get the smoothing parameter.
Definition at line 124 of file rmsprop.hpp.
◆ Alpha() [2/2]
|
inline |
Modify the smoothing parameter.
Definition at line 126 of file rmsprop.hpp.
◆ BatchSize() [1/2]
|
inline |
Get the batch size.
Definition at line 119 of file rmsprop.hpp.
◆ BatchSize() [2/2]
|
inline |
Modify the batch size.
Definition at line 121 of file rmsprop.hpp.
◆ Epsilon() [1/2]
|
inline |
Get the value used to initialise the mean squared gradient parameter.
Definition at line 129 of file rmsprop.hpp.
◆ Epsilon() [2/2]
|
inline |
Modify the value used to initialise the mean squared gradient parameter.
Definition at line 131 of file rmsprop.hpp.
◆ MaxIterations() [1/2]
|
inline |
Get the maximum number of iterations (0 indicates no limit).
Definition at line 134 of file rmsprop.hpp.
◆ MaxIterations() [2/2]
|
inline |
Modify the maximum number of iterations (0 indicates no limit).
Definition at line 136 of file rmsprop.hpp.
◆ Optimize()
|
inline |
Optimize the given function using RMSProp.
The given starting point will be modified to store the finishing point of the algorithm, and the final objective value is returned.
- Template Parameters
-
DecomposableFunctionType Type of the function to be optimized.
- Parameters
-
function Function to optimize. iterate Starting point (will be modified).
- Returns
- Objective value of the final point.
Definition at line 108 of file rmsprop.hpp.
◆ Shuffle() [1/2]
|
inline |
Get whether or not the individual functions are shuffled.
Definition at line 144 of file rmsprop.hpp.
◆ Shuffle() [2/2]
|
inline |
Modify whether or not the individual functions are shuffled.
Definition at line 146 of file rmsprop.hpp.
◆ StepSize() [1/2]
|
inline |
Get the step size.
Definition at line 114 of file rmsprop.hpp.
◆ StepSize() [2/2]
|
inline |
Modify the step size.
Definition at line 116 of file rmsprop.hpp.
◆ Tolerance() [1/2]
|
inline |
Get the tolerance for termination.
Definition at line 139 of file rmsprop.hpp.
◆ Tolerance() [2/2]
|
inline |
Modify the tolerance for termination.
Definition at line 141 of file rmsprop.hpp.
The documentation for this class was generated from the following file:
- src/mlpack/core/optimizers/rmsprop/rmsprop.hpp
Generated by
