So I think it figured it out, but it still seems strange. I took d\beta = R_{t}(\theta_{x},\theta_{y},\theta_{z}) - X^{'}X^{T}(XX^{T})^{-1} where \theta_{x}, \theta_{y}, \theta_{z} are updated at each iteration by \theta_{x,y,z} = \theta_{x,y,z} - d\theta_{x,y,z}, and it appears to be...