LAPACK-like code to back-propagate derivatives through the Cholesky decomposition, with Matlab and Python demos:https://github.com/imurray/chol-rev …
-
I hoped this would happen :-). I pointer to other code (Python only) for differentiating the Cholesky decomposition:https://github.com/imurray/chol-rev/issues/1 …
@driainmurray TensorFlow also has a Cholesky op you can backprop through: https://www.tensorflow.org/versions/master/api_docs/python/math_ops.html#cholesky …
-
-
@fchollet Update: that doesn't work (get "No gradient defined" error).@alexggmatthews &@JamesHensman do have TF code, but not shipped yet.Thanks. Twitter will use this to make your timeline better. UndoUndo
-
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.