This class is based on Mini-batch Stochastic Gradient Descent class and simulates a new warm-started run/restart once a number of epochs are performed using the Snapshot ensembles technique. More...

Public Types
using	OptimizerType = SGD< UpdatePolicyType, SnapshotEnsembles >
	Convenience typedef for the internal optimizer construction. More...

Public Member Functions
	SnapshotSGDR (const size_t epochRestart=50, const double multFactor=2.0, const size_t batchSize=1000, const double stepSize=0.01, const size_t maxIterations=100000, const double tolerance=1e-5, const bool shuffle=true, const size_t snapshots=5, const bool accumulate=true, const UpdatePolicyType &updatePolicy=UpdatePolicyType())
	Construct the SnapshotSGDR optimizer with snapshot ensembles with the given function and parameters. More...

size_t	BatchSize () const
	Get the batch size. More...

size_t &	BatchSize ()
	Modify the batch size. 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 SGDR. 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...

std::vector< arma::mat >	Snapshots () const
	Get the snapshots. More...

std::vector< arma::mat > &	Snapshots ()
	Modify the snapshots. 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...

const UpdatePolicyType &	UpdatePolicy () const
	Get the update policy. More...

UpdatePolicyType &	UpdatePolicy ()
	Modify the update policy. More...

Detailed Description

template
<
typename
UpdatePolicyType
=
MomentumUpdate
>

class mlpack::optimization::SnapshotSGDR< UpdatePolicyType >

This class is based on Mini-batch Stochastic Gradient Descent class and simulates a new warm-started run/restart once a number of epochs are performed using the Snapshot ensembles technique.

For more information, please refer to:

@article{Loshchilov2016,
  title   = {{SGDR:} Stochastic Gradient Descent with Restarts},
  author  = {Ilya Loshchilov and Frank Hutter},
  journal = {CoRR},
  year    = {2016},
  url     = {https://arxiv.org/abs/1608.03983}
}

@inproceedings{Huang2017,
  title     = {Snapshot ensembles: Train 1, get m for free},
  author    = {Gao Huang, Yixuan Li, Geoff Pleiss, Zhuang Liu,
               John E. Hopcroft, and Kilian Q. Weinberger},
  booktitle = {Proceedings of the International Conference on Learning
               Representations (ICLR)},
  year      = {2017},
  url       = {https://arxiv.org/abs/1704.00109}
}

Template Parameters

UpdatePolicyType Update policy used during the iterative update process. By default the momentum update policy (see mlpack::optimization::MomentumUpdate) is used.

Definition at line 61 of file snapshot_sgdr.hpp.

Member Typedef Documentation

◆ OptimizerType

using OptimizerType = SGD<UpdatePolicyType, SnapshotEnsembles>

Convenience typedef for the internal optimizer construction.

Definition at line 65 of file snapshot_sgdr.hpp.

Constructor & Destructor Documentation

◆ SnapshotSGDR()

SnapshotSGDR	(	const size_t	epochRestart = `50`,
		const double	multFactor = `2.0`,
		const size_t	batchSize = `1000`,
		const double	stepSize = `0.01`,
		const size_t	maxIterations = `100000`,
		const double	tolerance = `1e-5`,
		const bool	shuffle = `true`,
		const size_t	snapshots = `5`,
		const bool	accumulate = `true`,
		const UpdatePolicyType &	updatePolicy = `UpdatePolicyType()`
	)

Construct the SnapshotSGDR optimizer with snapshot ensembles 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 for the task at hand. The maximum number of iterations refers to the maximum number of mini-batches that are processed.

Parameters

epochRestart	Initial epoch where decay is applied.
batchSize	Size of each mini-batch.
stepSize	Step size for each iteration.
maxIterations	Maximum number of iterations allowed (0 means no limit).
tolerance	Maximum absolute tolerance to terminate algorithm.
shuffle	If true, the mini-batch order is shuffled; otherwise, each mini-batch is visited in linear order.
snapshots	Maximum number of snapshots.
accumulate	Accumulate the snapshot parameter (default true).
updatePolicy	Instantiated update policy used to adjust the given parameters.

Member Function Documentation

◆ BatchSize() [1/2]

size_t BatchSize ( ) const

inline

Get the batch size.

Definition at line 111 of file snapshot_sgdr.hpp.

References SGD< UpdatePolicyType, DecayPolicyType >::BatchSize().

◆ BatchSize() [2/2]

size_t& BatchSize ( )

inline

Modify the batch size.

Definition at line 113 of file snapshot_sgdr.hpp.

References SGD< UpdatePolicyType, DecayPolicyType >::BatchSize().

◆ MaxIterations() [1/2]

size_t MaxIterations ( ) const

inline

Get the maximum number of iterations (0 indicates no limit).

Definition at line 121 of file snapshot_sgdr.hpp.

References SGD< UpdatePolicyType, DecayPolicyType >::MaxIterations().

◆ MaxIterations() [2/2]

size_t& MaxIterations ( )

inline

Modify the maximum number of iterations (0 indicates no limit).

Definition at line 123 of file snapshot_sgdr.hpp.

References SGD< UpdatePolicyType, DecayPolicyType >::MaxIterations().

◆ Optimize()

double Optimize	(	DecomposableFunctionType &	function,
		arma::mat &	iterate
	)

Optimize the given function using SGDR.

The given starting point will be modified to store the finishing point of the algorithm, and the final objective value is returned.

Parameters

function	Function to optimize.
iterate	Starting point (will be modified).

Returns: Objective value of the final point.

◆ Shuffle() [1/2]

bool Shuffle ( ) const

inline

Get whether or not the individual functions are shuffled.

Definition at line 131 of file snapshot_sgdr.hpp.

References SGD< UpdatePolicyType, DecayPolicyType >::Shuffle().

◆ Shuffle() [2/2]

bool& Shuffle ( )

inline

Modify whether or not the individual functions are shuffled.

Definition at line 133 of file snapshot_sgdr.hpp.

References SGD< UpdatePolicyType, DecayPolicyType >::Shuffle().

◆ Snapshots() [1/2]

std::vector<arma::mat> Snapshots ( ) const

inline

Get the snapshots.

Definition at line 136 of file snapshot_sgdr.hpp.

References SGD< UpdatePolicyType, DecayPolicyType >::DecayPolicy(), and SnapshotEnsembles::Snapshots().

◆ Snapshots() [2/2]

std::vector<arma::mat>& Snapshots ( )

inline

Modify the snapshots.

Definition at line 141 of file snapshot_sgdr.hpp.

References SGD< UpdatePolicyType, DecayPolicyType >::DecayPolicy(), and SnapshotEnsembles::Snapshots().

◆ StepSize() [1/2]

double StepSize ( ) const

inline

Get the step size.

Definition at line 116 of file snapshot_sgdr.hpp.

References SGD< UpdatePolicyType, DecayPolicyType >::StepSize().

◆ StepSize() [2/2]

double& StepSize ( )

inline

Modify the step size.

Definition at line 118 of file snapshot_sgdr.hpp.

References SGD< UpdatePolicyType, DecayPolicyType >::StepSize().

◆ Tolerance() [1/2]

double Tolerance ( ) const

inline

Get the tolerance for termination.

Definition at line 126 of file snapshot_sgdr.hpp.

References SGD< UpdatePolicyType, DecayPolicyType >::Tolerance().

◆ Tolerance() [2/2]

double& Tolerance ( )

inline

Modify the tolerance for termination.

Definition at line 128 of file snapshot_sgdr.hpp.

References SGD< UpdatePolicyType, DecayPolicyType >::Tolerance().

◆ UpdatePolicy() [1/2]

const UpdatePolicyType& UpdatePolicy ( ) const

inline

Get the update policy.

Definition at line 147 of file snapshot_sgdr.hpp.

References SGD< UpdatePolicyType, DecayPolicyType >::UpdatePolicy().

◆ UpdatePolicy() [2/2]

UpdatePolicyType& UpdatePolicy ( )

inline

Modify the update policy.

Definition at line 152 of file snapshot_sgdr.hpp.

References SGD< UpdatePolicyType, DecayPolicyType >::UpdatePolicy().

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

src/mlpack/core/optimizers/sgdr/snapshot_sgdr.hpp

Public Types

Public Member Functions

Detailed Description

template<typenameUpdatePolicyType=MomentumUpdate> class mlpack::optimization::SnapshotSGDR< UpdatePolicyType >

Member Typedef Documentation

◆ OptimizerType

Constructor & Destructor Documentation

◆ SnapshotSGDR()

Member Function Documentation

◆ BatchSize() [1/2]

◆ BatchSize() [2/2]

◆ MaxIterations() [1/2]

◆ MaxIterations() [2/2]

◆ Optimize()

◆ Shuffle() [1/2]

◆ Shuffle() [2/2]

◆ Snapshots() [1/2]

◆ Snapshots() [2/2]

◆ StepSize() [1/2]

◆ StepSize() [2/2]

◆ Tolerance() [1/2]

◆ Tolerance() [2/2]

◆ UpdatePolicy() [1/2]

◆ UpdatePolicy() [2/2]

template
<
typename
UpdatePolicyType
=
MomentumUpdate
>

class mlpack::optimization::SnapshotSGDR< UpdatePolicyType >