pulsatrix::SGDOptimizer Class Reference

param -= learning_rate * grad, per parameter, for every parameter a Module exposes. More...

#include <sgd_optimizer.hpp>

Public Member Functions
	SGDOptimizer (float learning_rate)
	Constructs an SGD optimizer.
void	step (Module &module)
	Applies one SGD update to every parameter the module exposes.
void	zero_grad (Module &module)
	Resets every parameter's gradient to zero.

Detailed Description

param -= learning_rate * grad, per parameter, for every parameter a Module exposes.

Constructor & Destructor Documentation

SGDOptimizer()

pulsatrix::SGDOptimizer::SGDOptimizer ( float  learning_rate )

inlineexplicit

Constructs an SGD optimizer.

Parameters

learning_rate

Step size.

Member Function Documentation

step()

void pulsatrix::SGDOptimizer::step

(

Module &

module

)

Applies one SGD update to every parameter the module exposes.

Parameters

module

Module to update. Safe no-op if it has no parameters.

Note

Device-generic: runs on Cpu, Cuda or Hip tensors (GPU-native-kernels Mission 1).

zero_grad()

void pulsatrix::SGDOptimizer::zero_grad

(

Module &

module

)

Resets every parameter's gradient to zero.

Parameters

module

Module whose gradients to reset. Safe no-op if it has no parameters.

---

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

• include/pulsatrix/sgd_optimizer.hpp