v0.1.0-alpha.0
Pre-release
Pre-release
Updates
- Add Maximum Mean Discrepancy (
MMD
). (#60) - Add the Wasserstein distance (
WassersteinDistance
). (#60) - Add inverse multi-quadratic radial basis function (RBF) kernel. (#60)
- Remove the
log_likelihood
method. (#62) - Remove the
NLL
class. (#62) - Add
LogProb
andProb
instead ofNLL
. (#62) - Add
log_prob
andprob
methods in Distribution API each of which performs as the instance ofLogProb
andProb
respectively. (#62) - Rename the
LossExpectation
class toExpectation
. (#62) - Add the
expectation
method in Loss API as the instance of theExpectation
class. (#62) - Rename the
estimation
method in Loss API toeval
(followed by model.eval() on PyTorch). (#62) - Remove flow implementations for now. (#62)