Tomogravity estimation for a single time point using L-BFGS-B

Description

Tomogravity estimation for a single time point using L-BFGS-B

Usage

1
2
tomogravity.fit(yt, A, srcDstInd, lambda, N = 1, normalize = FALSE,
  lower = 0, control = list())

Arguments

yt

length-m numeric vector of observed aggregate flows at time t

A

m x k routing matrix

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.

N

total traffic for normalization. Unused if normalized is FALSE.

normalize

If TRUE, xt and yt are scaled by N. Typically used in conjunction with calcN to normalize traffic to proportions, easing the tuning of lambda.

lower

Component-wise lower bound for xt in L-BFGS-B optimization.

control

List of control information for optim.

Value

A list as returned by optim, with element par containing the estimated point-to-point flows and elementer gr containing the analytic gradient evaluated at the estimate.

See Also

Other tomogravity: tomogravity

Examples

1
2
3
4
data(cmu)
srcDstInd <- getSrcDstIndices(cmu$A.full)
estimate <- tomogravity.fit(yt=cmu$Y.full[1, ], A=cmu$A.full,
     srcDstInd=srcDstInd, lambda=0.01)

Want to suggest features or report bugs for rdrr.io? Use the GitHub issue tracker.