GenerativeAdversarialNets.PDF

Generative Adversarial Nets Ian J. Goodfellow,? Jean Pouget-Abadie,? Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair,? Aaron Courville, Yoshua Bengio§ Departement′ d’informatique et de recherche operationnelle′ Universite′ de Montreal′ Montreal,′ QC H3C 3J7 Abstract We propose a new framework for estimating generative models via an adversar- ial process, 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 train- ing 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 1 distribution and D equal to 2 everywhere. In the case where G and D are de?ned by multilayer perceptrons, the entire system can be trained with backpropagation. There is no need for any Markov chains or unrolled approximate inference net- works during either training or generation of samples. Experiments demonstrate the potential of the framework through qualitative and quantitative evaluation of the generated samples. 1 Introduction The promise of deep learning is to discover rich, hierarchical models [2] that represent probability distributions over the kinds of data encountered in arti?cial intelligence applications, such as natural images, audio waveforms containing speech, and symbols in natural language corpora. So far, the most striking successes in deep learning have involved discriminative models, usually those that map a high-dimensional, rich sen