I'm trying to use the EM to estimate some parameters. I've programmed and it delivers. The problem however is that for each run of my programme, it can take either 5 seconds, 1min, 3min or more to give an estimate. So, I'm looking to accelerate the EM algorithm on the internet and I've find myself swamped with methods. There are so many - like Aitken's method, Louis', generalized conjugate approach, generalized gradient, hybrid methods like the ones based on Newton-Raphson, the ECM, and the ECME... (probably still missing some) - that I do not know which one to choose, and I simply do not have the time to study all of them by myself. Hence, I ask for your help in deciding which one I should study.
I'm sampling from $ Y_n \sim \pi N(\theta_1+\theta_0Y_{n-1},\sigma^2)+(1-\pi)N(\theta_2+\theta_0Y_{n-1},\sigma^2)$ and I'm using the EM to estimate $\theta_1,\theta_2,\sigma,\pi$
