%0 Generic %1 rosca2017variational %A Rosca, Mihaela %A Lakshminarayanan, Balaji %A Warde-Farley, David %A Mohamed, Shakir %D 2017 %K GAN autoencoder %T Variational Approaches for Auto-Encoding Generative Adversarial Networks %U http://arxiv.org/abs/1706.04987 %X Auto-encoding generative adversarial networks (GANs) combine the standard GAN algorithm, which discriminates between real and model-generated data, with a reconstruction loss given by an auto-encoder. Such models aim to prevent mode collapse in the learned generative model by ensuring that it is grounded in all the available training data. In this paper, we develop a principle upon which auto-encoders can be combined with generative adversarial networks by exploiting the hierarchical structure of the generative model. The underlying principle shows that variational inference can be used a basic tool for learning, but with the in- tractable likelihood replaced by a synthetic likelihood, and the unknown posterior distribution replaced by an implicit distribution; both synthetic likelihoods and implicit posterior distributions can be learned using discriminators. This allows us to develop a natural fusion of variational auto-encoders and generative adversarial networks, combining the best of both these methods. We describe a unified objective for optimization, discuss the constraints needed to guide learning, connect to the wide range of existing work, and use a battery of tests to systematically and quantitatively assess the performance of our method.

@misc{rosca2017variational, abstract = {Auto-encoding generative adversarial networks (GANs) combine the standard GAN algorithm, which discriminates between real and model-generated data, with a reconstruction loss given by an auto-encoder. Such models aim to prevent mode collapse in the learned generative model by ensuring that it is grounded in all the available training data. In this paper, we develop a principle upon which auto-encoders can be combined with generative adversarial networks by exploiting the hierarchical structure of the generative model. The underlying principle shows that variational inference can be used a basic tool for learning, but with the in- tractable likelihood replaced by a synthetic likelihood, and the unknown posterior distribution replaced by an implicit distribution; both synthetic likelihoods and implicit posterior distributions can be learned using discriminators. This allows us to develop a natural fusion of variational auto-encoders and generative adversarial networks, combining the best of both these methods. We describe a unified objective for optimization, discuss the constraints needed to guide learning, connect to the wide range of existing work, and use a battery of tests to systematically and quantitatively assess the performance of our method.}, added-at = {2017-08-18T11:01:19.000+0200}, author = {Rosca, Mihaela and Lakshminarayanan, Balaji and Warde-Farley, David and Mohamed, Shakir}, biburl = {https://www.bibsonomy.org/bibtex/2c5d21ef1d6d12ef6b21fdbafd8d69c8d/daschloer}, description = {Variational Approaches for Auto-Encoding Generative Adversarial Networks}, interhash = {1d2ebde962b88491d5ef028d5e7aa011}, intrahash = {c5d21ef1d6d12ef6b21fdbafd8d69c8d}, keywords = {GAN autoencoder}, note = {cite arxiv:1706.04987}, timestamp = {2017-10-04T16:28:59.000+0200}, title = {Variational Approaches for Auto-Encoding Generative Adversarial Networks}, url = {http://arxiv.org/abs/1706.04987}, year = 2017 }