The maximum likelihood principle advocates parameter estimation via
opti...
State-of-the-art automatic augmentation methods (e.g., AutoAugment and
R...
We present a framework for video modeling based on denoising diffusion
p...
We consider image completion from the perspective of amortized inference...
We explore the effects of architecture and training objective choice on
...
In this work we demonstrate how existing software tools can be used to
a...
Deterministic models are approximations of reality that are easy to inte...
Existing approaches to amortized inference in probabilistic programs wit...
Probabilistic programming languages (PPLs) are receiving widespread atte...