LearningRate类 参考

详细描述

The base class about learning rate for descent-based minimizers.

This is the interface used in descent based minimizers. (eg, GradientDescendUpdater::update_variable(SGVector<float64_t> variable_reference, SGVector<float64_t> gradient) )

在文件 LearningRate.h 第 46 行定义.

类 LearningRate 继承关系图:

Public 成员函数
virtual float64_t	get_learning_rate (int32_t iter_counter)=0
virtual void	update_context (CMinimizerContext *context)=0
virtual void	load_from_context (CMinimizerContext *context)=0

成员函数说明

virtual float64_t get_learning_rate ( int32_t  iter_counter )

pure virtual

Get a learning rate for descent direction Note that the learning rate usually is positive

参数

iter_counter

the number of iterations

返回

the learning rate (A.K.A step size/length)

在 ConstLearningRate , 以及 InverseScalingLearningRate 内被实现.

virtual void load_from_context ( CMinimizerContext *  context )

pure virtual

Load the given context object to restore mutable variables

参数

context

a context object

在 InverseScalingLearningRate , 以及 ConstLearningRate 内被实现.

virtual void update_context ( CMinimizerContext *  context )

pure virtual

Update a context object to store mutable variables used in learning rate

参数

context

a context object

在 InverseScalingLearningRate , 以及 ConstLearningRate 内被实现.

---

该类的文档由以下文件生成:

• LearningRate.h