ngQ: Gradient of the E-step function Q

In RestoreNet: Random-Effects Stochastic Reaction Networks

Gradient of the E-step function Q

Description

Gradient -\nabla Q of the negative E-step function -Q of the expectation-maximization algorithm

Usage

ngQ(theta, euy_curr, vuy_curr, M, M_bdiag, y, V, VCNs, nObs, dW)

Arguments

theta	p-dimensional vector parameter.
euy_curr	current value of the conditional expectation E[u \vert y] of u given y, where u and y are the latent and observed states respectively.
vuy_curr	current value of the conditional variance V[u \vert y] of u given y, where u and y are the latent and observed states respectively.
M	A n \times K dimensional (design) matrix.
M_bdiag	An \times Jp dimensional block-diagonal design matrix. Each j-th block (j = 1,\dots,J) is a n_j \times p dimensional design matrix for the j-th clone.
y	n-dimensional vector of the time-adjacent cellular increments
V	A p \times K dimensional net-effect matrix.
VCNs	A n-dimensional vector including values of the vector copy number corresponding to the cell counts of y.
nObs	A K-dimensional vector including the frequencies of each clone k (k = 1,\dots,K).
dW	p-dimensional list of the partial derivatives of W w.r.t. theta.

Value

p-dimensional vector of the gradient -\nabla Q of the negative E-step function -Q.

RestoreNet documentation built on May 29, 2024, 4 a.m.