You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I think we could do this by numerically approximating the Jacobian via finite difference. Alternatively we could stack a bunch of grad()s, computing the determinant as in this suggestion:
It would be nice to make this test generic like the other tests in TestTransforms.
Note that this might not work for StickBreakingTransform because the det computation is over a non-square matrix since the source and target spaces have different dimensions.
The text was updated successfully, but these errors were encountered:
fritzo
changed the title
Write finite-difference tests for .log_abs_det_jacobian() methods
Write finite-difference tests for .log_abs_det_jacobian() methods
Jan 28, 2018
fritzo
changed the title
Write finite-difference tests for .log_abs_det_jacobian() methods
Write tests for .log_abs_det_jacobian() methods
Jan 29, 2018
I think we could do this by numerically approximating the Jacobian via finite difference. Alternatively we could
stack
a bunch ofgrad()
s, computing the determinant as in this suggestion:It would be nice to make this test generic like the other tests in
TestTransforms
.Note that this might not work for
StickBreakingTransform
because the det computation is over a non-square matrix since the source and target spaces have different dimensions.The text was updated successfully, but these errors were encountered: