Tuan Le

icon indicating a website link https://tuanle618.github.io icon indicating an email [email protected]

icon location Berlin icon location Research on representation learning for molecular structures. Broad interest in statistics, probabilistic modelling and optimal transport theory.

Results 1 issues of Tuan Le

Use cached version of PHM-weight matrix after training.

General idea: When training is finished, the PHM-weight matrix does not have to be constructed by a sum of Kronecker products in every forward pass. One could check for `self.train`...

enhancement