We systematically study a wide variety of image-based generative models
...
We propose TR0N, a highly general framework to turn pre-trained uncondit...
Likelihood-based deep generative models have recently been shown to exhi...
Given a pair of models with similar training set performance, it is natu...
Deep learning has had tremendous success at learning low-dimensional
rep...
Natural data observed in ℝ^n is often constrained to an
m-dimensional ma...
Probability distributions supported on the simplex enjoy a wide range of...
Likelihood-based, or explicit, deep generative models use neural network...
Skills or low-level policies in reinforcement learning are temporally
ex...
Deep generative models trained by maximum likelihood remain very popular...
Normalizing flows are invertible neural networks with tractable
change-o...
Multi-goal reaching is an important problem in reinforcement learning ne...
Modern deep learning is primarily an experimental science, in which empi...
Simplex-valued data appear throughout statistics and machine learning, f...
The Gumbel-Softmax is a continuous distribution over the simplex that is...
Variational autoencoders (VAE) have quickly become a central tool in mac...
Gaussian processes are the leading class of distributions on random
func...
Maximum entropy modeling is a flexible and popular framework for formula...