// MarginalNormal returns the marginal distribution of the given input variables.
// That is, MarginalNormal returns
// p(x_i) = \int_{x_o} p(x_i | x_o) p(x_o) dx_o
// where x_i are the dimensions in the input, and x_o are the remaining dimensions.
// The input src is passed to the call to NewNormal.
func (n *Normal) MarginalNormal(vars []int, src *rand.Rand) (*Normal, bool) {
newMean := make([]float64, len(vars))
for i, v := range vars {
newMean[i] = n.mu[v]
}
n.setSigma()
var s mat64.SymDense
s.SubsetSym(n.sigma, vars)
return NewNormal(newMean, &s, src)
}
func ExampleSymDense_SubsetSym() {
n := 5
s := mat64.NewSymDense(5, nil)
count := 1.0
for i := 0; i < n; i++ {
for j := i; j < n; j++ {
s.SetSym(i, j, count)
count++
}
}
fmt.Println("Original matrix:")
fmt.Printf("%0.4v\n\n", mat64.Formatted(s))
// Take the subset {0, 2, 4}
var sub mat64.SymDense
sub.SubsetSym(s, []int{0, 2, 4})
fmt.Println("Subset {0, 2, 4}")
fmt.Printf("%0.4v\n\n", mat64.Formatted(&sub))
// Take the subset {0, 0, 4}
sub.SubsetSym(s, []int{0, 0, 4})
fmt.Println("Subset {0, 0, 4}")
fmt.Printf("%0.4v\n\n", mat64.Formatted(&sub))
// Output:
// Original matrix:
// ⎡ 1 2 3 4 5⎤
// ⎢ 2 6 7 8 9⎥
// ⎢ 3 7 10 11 12⎥
// ⎢ 4 8 11 13 14⎥
// ⎣ 5 9 12 14 15⎦
//
// Subset {0, 2, 4}
// ⎡ 1 3 5⎤
// ⎢ 3 10 12⎥
// ⎣ 5 12 15⎦
//
// Subset {0, 0, 4}
// ⎡ 1 1 5⎤
// ⎢ 1 1 5⎥
// ⎣ 5 5 15⎦
}
// ConditionNormal returns the Normal distribution that is the receiver conditioned
// on the input evidence. The returned multivariate normal has dimension
// n - len(observed), where n is the dimension of the original receiver. The updated
// mean and covariance are
// mu = mu_un + sigma_{ob,un}^T * sigma_{ob,ob}^-1 (v - mu_ob)
// sigma = sigma_{un,un} - sigma_{ob,un}^T * sigma_{ob,ob}^-1 * sigma_{ob,un}
// where mu_un and mu_ob are the original means of the unobserved and observed
// variables respectively, sigma_{un,un} is the unobserved subset of the covariance
// matrix, sigma_{ob,ob} is the observed subset of the covariance matrix, and
// sigma_{un,ob} are the cross terms. The elements of x_2 have been observed with
// values v. The dimension order is preserved during conditioning, so if the value
// of dimension 1 is observed, the returned normal represents dimensions {0, 2, ...}
// of the original Normal distribution.
//
// ConditionNormal returns {nil, false} if there is a failure during the update.
// Mathematically this is impossible, but can occur with finite precision arithmetic.
func (n *Normal) ConditionNormal(observed []int, values []float64, src *rand.Rand) (*Normal, bool) {
if len(observed) == 0 {
panic("normal: no observed value")
}
if len(observed) != len(values) {
panic("normal: input slice length mismatch")
}
for _, v := range observed {
if v < 0 || v >= n.Dim() {
panic("normal: observed value out of bounds")
}
}
ob := len(observed)
unob := n.Dim() - ob
obMap := make(map[int]struct{})
for _, v := range observed {
if _, ok := obMap[v]; ok {
panic("normal: observed dimension occurs twice")
}
obMap[v] = struct{}{}
}
if len(observed) == n.Dim() {
panic("normal: all dimensions observed")
}
unobserved := make([]int, 0, unob)
for i := 0; i < n.Dim(); i++ {
if _, ok := obMap[i]; !ok {
unobserved = append(unobserved, i)
}
}
mu1 := make([]float64, unob)
for i, v := range unobserved {
mu1[i] = n.mu[v]
}
mu2 := make([]float64, ob) // really v - mu2
for i, v := range observed {
mu2[i] = values[i] - n.mu[v]
}
n.setSigma()
var sigma11, sigma22 mat64.SymDense
sigma11.SubsetSym(n.sigma, unobserved)
sigma22.SubsetSym(n.sigma, observed)
sigma21 := mat64.NewDense(ob, unob, nil)
for i, r := range observed {
for j, c := range unobserved {
v := n.sigma.At(r, c)
sigma21.Set(i, j, v)
}
}
var chol mat64.Cholesky
ok := chol.Factorize(&sigma22)
if !ok {
return nil, ok
}
// Compute sigma_{2,1}^T * sigma_{2,2}^-1 (v - mu_2).
v := mat64.NewVector(ob, mu2)
var tmp, tmp2 mat64.Vector
err := tmp.SolveCholeskyVec(&chol, v)
if err != nil {
return nil, false
}
tmp2.MulVec(sigma21.T(), &tmp)
// Compute sigma_{2,1}^T * sigma_{2,2}^-1 * sigma_{2,1}.
// TODO(btracey): Should this be a method of SymDense?
var tmp3, tmp4 mat64.Dense
err = tmp3.SolveCholesky(&chol, sigma21)
if err != nil {
return nil, false
}
tmp4.Mul(sigma21.T(), &tmp3)
for i := range mu1 {
mu1[i] += tmp2.At(i, 0)
}
// TODO(btracey): If tmp2 can constructed with a method, then this can be
// replaced with SubSym.
for i := 0; i < len(unobserved); i++ {
for j := i; j < len(unobserved); j++ {
v := sigma11.At(i, j)
sigma11.SetSym(i, j, v-tmp4.At(i, j))
}
}
return NewNormal(mu1, &sigma11, src)
}
