Open chrism0dwk opened 3 years ago
@csuter Smooth switch to tfp.experimental.distributions.MultivariateNormalPrecisionFactorLinearOperator
here, but seeing warnings:
WARNING:tensorflow:Using (possibly slow) default implementation of determinant. Requires conversion to a dense matrix and O(N^3) operations.
I guess this is reasonable, though unavoidable?
Use LinearOperatorLowerTriangular
for the precision factor to avoid this.
Potential speed improvement, cutting out an explicit matrix inverse.