Generative Adversarial Nets

We propose a new framework for estimating generative models via adversarial nets, in which we simultaneously train two models: a generative model G that captures the data distribution, and a discriminative model D that estimates the probability that a sample came from the training data rather than G. The training procedure for G is to maximize the probability of D making a mistake. This framework corresponds to a minimax two-player game. In the space of arbitrary functions G and D, a unique solution exists, with G recovering the training data distribution and D equal to 1/2 everywhere. In the case where G and D are defined by multilayer perceptrons, the entire system can be trained with backpropagation. There is no need for any Markov chains or unrolled approximate inference networks during either training or generation of samples. Experiments demonstrate the potential of the framework through qualitative and quantitatively evaluation of the generated samples.

Authors

• Ian Goodfellow Université de Montréal
• Jean Pouget-Abadie
• Mehdi Mirza University of Montreal
• Bing Xu
• David Warde-Farley
• Sherjil Ozair Mila, Université de Montréal
• Aaron Courville
• Yoshua Bengio Mila University of Montreal

Keywords

No keywords are indexed for this paper.