The computation necessary for training Transformer-based language models...
Likelihood-free inference methods typically make use of a distance betwe...
Score-based divergences have been widely used in machine learning and
st...
Model misspecification can create significant challenges for the
impleme...
Counterfactual explanations (CEs) are a practical tool for demonstrating...
We propose a new model that estimates uncertainty in a single forward pa...
We show that the gradient estimates used in training Deep Gaussian Proce...
The number of parameters in state of the art neural networks has drastic...