cpu_mlp::StochasticMinimizer< V, M > Class Template Reference

Base class for Stochastic Minimizers. More...

#include <stochastic_minimizer.hpp>

Inheritance diagram for cpu_mlp::StochasticMinimizer< V, M >:

Collaboration diagram for cpu_mlp::StochasticMinimizer< V, M >:

Public Member Functions
virtual	~StochasticMinimizer ()=default
void	setMaxIterations (int max_iters)
	Sets the maximum number of iterations. More...
void	setStepSize (double s)
	Sets the step size (learning rate). More...
void	setTolerance (double tol)
	Sets the tolerance for convergence (full gradient norm). More...
void	setRecorder (::IterationRecorder< CpuBackend > *recorder)
	Attach a recorder for loss/grad history. More...

Protected Attributes
unsigned int	_max_iters = 1000
unsigned int	_iters = 0
double	_tol = 1e-4
double	step_size = 0.01
::IterationRecorder< CpuBackend > *	recorder_ = nullptr
	Optional recorder for diagnostics. More...

Detailed Description

template<typename V, typename M>
class cpu_mlp::StochasticMinimizer< V, M >

Base class for Stochastic Minimizers.

Provides common storage for stochastic optimization parameters like step size and iteration limits.

Constructor & Destructor Documentation

~StochasticMinimizer()

template<typename V , typename M >

virtual cpu_mlp::StochasticMinimizer< V, M >::~StochasticMinimizer ( )

virtualdefault

Member Function Documentation

setMaxIterations()

template<typename V , typename M >

void cpu_mlp::StochasticMinimizer< V, M >::setMaxIterations ( int  max_iters )

inline

Sets the maximum number of iterations.

Parameters

max_iters

Limit on iterations.

setRecorder()

template<typename V , typename M >

void cpu_mlp::StochasticMinimizer< V, M >::setRecorder ( ::IterationRecorder< CpuBackend > *  recorder )

inline

Attach a recorder for loss/grad history.

Parameters

recorder

Recorder instance (may be null).

setStepSize()

template<typename V , typename M >

void cpu_mlp::StochasticMinimizer< V, M >::setStepSize ( double  s )

inline

Sets the step size (learning rate).

Parameters

s	Step size.

setTolerance()

template<typename V , typename M >

void cpu_mlp::StochasticMinimizer< V, M >::setTolerance ( double  tol )

inline

Sets the tolerance for convergence (full gradient norm).

Parameters

tol	Tolerance value.

Member Data Documentation

_iters

template<typename V , typename M >

unsigned int cpu_mlp::StochasticMinimizer< V, M >::_iters = 0

protected

_max_iters

template<typename V , typename M >

unsigned int cpu_mlp::StochasticMinimizer< V, M >::_max_iters = 1000

protected

_tol

template<typename V , typename M >

double cpu_mlp::StochasticMinimizer< V, M >::_tol = 1e-4

protected

recorder_

template<typename V , typename M >

::IterationRecorder<CpuBackend>* cpu_mlp::StochasticMinimizer< V, M >::recorder_ = nullptr

protected

Optional recorder for diagnostics.

step_size

template<typename V , typename M >

double cpu_mlp::StochasticMinimizer< V, M >::step_size = 0.01

protected

---

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

• src/minimizer/stochastic_minimizer.hpp