dobj.dxt.tomogravity: Analytic gradient of objective function of Zhang et al. 2003
Description
Requires bounded optimization to maintain positive OD
flows, and only those flows that are not deterministically
zero should be included in the estimation.
Usage
dobj.dxt.tomogravity(xt, yt, A, srcDstInd, lambda)
Arguments
xt
length-k numeric vector of point-to-point
flows
yt
length-m numeric vector of observed aggregate
flows
A
m x k routing matrix, yt = A xt
srcDstInd
list of source and destination flow
indices corresponding to each point-to-point flow, as
produced by getSrcDstIndices
lambda
regularization parameter for mutual
information prior. Note that this is scaled by the
squared total traffic in the objective function before
scaling the mututal information prior.
Value
numeric vector of length k containing gradient of objective
function with respect to xt