How to speed up this double cycle?

Question

I am programming an algorithm for maximizing expectations with R. To speed up the calculation, I would like to quote this bottleneck. I know that N about a hundred times.

MyLoglik = 0
for (i in c(1:N))
{
 for (j in c(1:k))
 {
  MyLoglik = MyLoglik + MyTau[i,j]*log(MyP[j]*MyF(MyD[i,], MyMu[j,], MyS[[j]]))
 }
}

There is also this list of matrices:

MyDf.list <- vector("list", k)
for(i in 1:k)
{
 MyDf.list[[i]] <- matrix(0,d,d)
 for (j in c(1:N))
 {
  MyDf.list[[i]] = MyDf.list[[i]] + MyTau[j,i]*as.numeric((MyD[j,]-MyMu[i,])) %*% t(as.numeric(MyD[j,]-MyMu[i,]))  
 }
 MyDf.list[[i]] = MyDf.list[[i]] / MyM[i]
}

---

I sped things up a bit using:

MyLoglik = 0
for (j in c(1:k))
{
 MyR= apply(MyD, 1, function(x) log(MyP[j]*MyF(x, MyMu[j,], MyS[[j]])))
 MyLoglik = MyLoglik + sum(MyTau[,j]*MyR)
}

and

d = dim(MyD)[2]
MyDf.list <- vector("list", k)
for(i in 1:k)
{
 MyDf.list[[i]] <- matrix(0,d,d)
 MyR= apply(MyD, 1, function(x) as.numeric((x-MyMu[i,])) %*% t(as.numeric(x-MyMu[i,])))
 MyDf.list[[i]] = matrix(rowSums(t(MyTau[,i]*t(MyR))) / MyM[i],d,d)
}

Answer 1

For the first, I assume MyF is the function you created? If you can make sure that it takes your matrices and lists as input and outputs the matrix, you can do something like:

MyLoglik = sum(MyTau%*%log(MyP)) + sum(MyTau*log(MyF(MyD, MyMu, MyS)))

, , , . , 3- ? MyDf.array [i, j, k] N, d, d ( d, d, N).

Answer 2

, , C- R . () ( !), C- , ! , , 'myF'

R- , ( , !) .

, , ? myF? , ?

Answer 3

, , : A[i,j] = A[j,i]