◆ categorical_logit_glm_beta_derivative()

__kernel void stan::math::opencl_kernels::categorical_logit_glm_beta_derivative	(	__global double *	beta_derivative,
		__global double *	temp,
		const __global int *	y,
		const __global double *	x,
		const int	N_instances,
		const int	N_attributes,
		const int	N_classes,
		const int	is_y_vector
	)

Calculates derivative wrt beta.

Must be run with global size of local_size*N_attributes.

Parameters

[in,out]	beta_derivative	derivative wrt beta
	temp	temporary workspace of size global_size*N_classes
[in]	y	a scalar or vector of classes
[in]	x	design matrix
	N_instances	number of instances
	N_attributes	number of attributes
	N_classes	number of classes
	is_y_vector	0 or 1 - whether y is a vector (alternatively it is a scalar)