SparseVariationalApproximation breaks with PDMats.jl v0.11.8

[simsurace]

When running the example, the optimization does not work properly, i.e. the optimal covariance matrix of the sparse approximation remains diagonal.

[simsurace]

So I guess ApproximateGPs.jl depends on some internals of PDMats.jl then.

[devmotion]

Indeed, it seems SparseVariationalApproximation uses the unexported PDMats.chol_lower:

ApproximateGPs.jl/src/SparseVariationalApproximationModule.jl

Line 12 in dec9785

using PDMats: chol_lower, ScalMat

(BTW it also uses some other internals such as https://github.com/JuliaGaussianProcesses/ApproximateGPs.jl/blob/master/src/SparseVariationalApproximationModule.jl#L26)

[st--]

(BTW it also uses some other internals such as https://github.com/JuliaGaussianProcesses/ApproximateGPs.jl/blob/master/src/SparseVariationalApproximationModule.jl#L26)

these are actually defined in https://github.com/JuliaGaussianProcesses/ApproximateGPs.jl/blob/master/src/utils.jl

[devmotion]

Fixed by #133.