Timezone: »

f-GAN: Training Generative Neural Samplers using Variational Divergence Minimization
Sebastian Nowozin · Botond Cseke · Ryota Tomioka

Wed Dec 07 09:00 AM -- 12:30 PM (PST) @ Area 5+6+7+8 #106
Generative neural networks are probabilistic models that implement sampling using feedforward neural networks: they take a random input vector and produce a sample from a probability distribution defined by the network weights. These models are expressive and allow efficient computation of samples and derivatives, but cannot be used for computing likelihoods or for marginalization. The generative-adversarial training method allows to train such models through the use of an auxiliary discriminative neural network. We show that the generative-adversarial approach is a special case of an existing more general variational divergence estimation approach. We show that any $f$-divergence can be used for training generative neural networks. We discuss the benefits of various choices of divergence functions on training complexity and the quality of the obtained generative models.

Author Information

Sebastian Nowozin (Microsoft Research)
Botond Cseke (Microsoft Research)
Ryota Tomioka (MSRC)

More from the Same Authors