Diffusion models excel at generating photorealistic images from text-que...
Recovering the latent factors of variation of high dimensional data has ...
Deep ensembles (DE) have been successful in improving model performance ...
Multimodal image-text models have shown remarkable performance in the pa...
Since out-of-distribution generalization is a generally ill-posed proble...
Machine learning models based on the aggregated outputs of submodels, ei...
Uncertainty estimation in deep learning has recently emerged as a crucia...
Ensembles of deep neural networks have achieved great success recently, ...
High-quality estimates of uncertainty and robustness are crucial for num...
Isotropic Gaussian priors are the de facto standard for modern Bayesian
...
Ensembles over neural network weights trained from different random
init...
We propose automated augmented conjugate inference, a new inference meth...
During the past five years the Bayesian deep learning community has deve...
We propose a new scalable multi-class Gaussian process classification
ap...
Many machine learning problems involve Monte Carlo gradient estimators. ...
Dynamic topic models (DTMs) model the evolution of prevalent themes in
l...
We propose an efficient stochastic variational approach to GP classifica...
We propose a fast inference method for Bayesian nonlinear support vector...