Simplicial complexes prove effective in modeling data with multiway
depe...
Selecting hyperparameters in deep learning greatly impacts its effective...
Deep neural networks (DNNs) have found successful applications in many
f...
The linearized-Laplace approximation (LLA) has been shown to be effectiv...
We study the class of location-scale or heteroscedastic noise models (LS...
Data augmentation is commonly applied to improve performance of deep lea...
Pre-trained contextual representations have led to dramatic performance
...
In recent years, the transformer has established itself as a workhorse i...
Bayesian formulations of deep learning have been shown to have compellin...
Marginal-likelihood based model-selection, even though promising, is rar...
In this paper we argue that in Bayesian deep learning, the frequently
ut...
In this thesis, we disentangle the generalized Gauss-Newton and approxim...
Continually learning new skills is important for intelligent systems, ye...
The Black Box Variational Inference (Ranganath et al. (2014)) algorithm
...
Deep neural networks (DNN) and Gaussian processes (GP) are two powerful
...
Learning distributed representations of documents has pushed the
state-o...