Group-invariant generative adversarial networks (GANs) are a type of GAN...
We rigorously quantify the improvement in the sample complexity of
varia...
Lipschitz regularized f-divergences are constructed by imposing a bound ...
We propose a new family of regularized Rényi divergences parametrized no...
Generative adversarial networks (GANs), a class of distribution-learning...
Probabilistic graphical models are a fundamental tool in probabilistic
m...
We develop a general framework for constructing new information-theoreti...
We derive a new variational formula for the Rényi family of divergences,...
Variational-principle-based methods that relate expectations of a quanti...