Unrolled Generative Adversarial Networks

We introduce a method to stabilize Generative Adversarial Networks (GANs) by defining the generator objective with respect to an unrolled optimization of the discriminator. This allows training to be adjusted between using the optimal discriminator in the generator's objective, which is ideal but infeasible in practice, and using the current value of the discriminator, which is often unstable and leads to poor solutions. We show how this technique solves the common problem of mode collapse, stabilizes training of GANs with complex recurrent generators, and increases diversity and coverage of the data distribution by the generator.

[1]  J. Danskin.  The Theory of Max-Min and its Application to Weapons Allocation Problems , 1967 .

[2]  Geoffrey E. Hinton,et al.  The Helmholtz Machine , 1995, Neural Computation.

[3]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[4]  Yishay Mansour,et al.  Nash Convergence of Gradient Dynamics in General-Sum Games , 2000, UAI.

[5]  Manuela M. Veloso,et al.  Multiagent learning using a variable learning rate , 2002, Artif. Intell..

[6]  Barak A. Pearlmutter,et al.  Reverse-mode AD in a functional framework: Lambda the ultimate backpropagator , 2008, TOPL.

[7]  Victor R. Lesser,et al.  Multi-Agent Learning with Policy Prediction , 2010, AAAI.

[8]  A. Juditsky,et al.  5 First-Order Methods for Nonsmooth Convex Large-Scale Optimization , I : General Purpose Methods , 2010 .

[9]  Yoshua Bengio,et al.  Understanding the difficulty of training deep feedforward neural networks , 2010, AISTATS.

[10]  Pascal Vincent,et al.  Stacked Denoising Autoencoders: Learning Useful Representations in a Deep Network with a Local Denoising Criterion , 2010, J. Mach. Learn. Res..

[11]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[12]  Max Welling,et al.  Auto-Encoding Variational Bayes , 2013, ICLR.

[13]  Andrew Zisserman,et al.  Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps , 2013, ICLR.

[14]  Daan Wierstra,et al.  Stochastic Back-propagation and Variational Inference in Deep Latent Gaussian Models , 2014, ArXiv.

[15]  Hod Lipson,et al.  Understanding Neural Networks Through Deep Visualization , 2015, ArXiv.

[16]  Surya Ganguli,et al.  Deep Unsupervised Learning using Nonequilibrium Thermodynamics , 2015, ICML.

[17]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[18]  Joshua B. Tenenbaum,et al.  Deep Convolutional Inverse Graphics Network , 2015, NIPS.

[19]  Pascal Vincent,et al.  GSNs : Generative Stochastic Networks , 2015, ArXiv.

[20]  Alex Graves,et al.  DRAW: A Recurrent Neural Network For Image Generation , 2015, ICML.

[21]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[22]  Yoshua Bengio,et al.  NICE: Non-linear Independent Components Estimation , 2014, ICLR.

[23]  Ryan P. Adams,et al.  Gradient-based Hyperparameter Optimization through Reversible Learning , 2015, ICML.

[24]  Matthias Bethge,et al.  Generative Image Modeling Using Spatial LSTMs , 2015, NIPS.

[25]  Alex Graves,et al.  Conditional Image Generation with PixelCNN Decoders , 2016, NIPS.

[26]  Yann LeCun,et al.  Energy-based Generative Adversarial Network , 2016, ICLR.

[27]  Pieter Abbeel,et al.  InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets , 2016, NIPS.

[28]  Marcin Andrychowicz,et al.  Learning to learn by gradient descent by gradient descent , 2016, NIPS.

[29]  Matthias Bethge,et al.  A note on the evaluation of generative models , 2015, ICLR.

[30]  Ruslan Salakhutdinov,et al.  Importance Weighted Autoencoders , 2015, ICLR.

[31]  Alex J. Champandard,et al.  Semantic Style Transfer and Turning Two-Bit Doodles into Fine Artworks , 2016, ArXiv.

[32]  Koray Kavukcuoglu,et al.  Pixel Recurrent Neural Networks , 2016, ICML.

[33]  Wojciech Zaremba,et al.  Improved Techniques for Training GANs , 2016, NIPS.

[34]  Bernt Schiele,et al.  Generative Adversarial Text to Image Synthesis , 2016, ICML.

[35]  Soumith Chintala,et al.  Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks , 2015, ICLR.

[36]  Xinyun Chen.  Under Review as a Conference Paper at Iclr 2017 Delving into Transferable Adversarial Ex- Amples and Black-box Attacks , 2016 .

[37]  Jascha Sohl-Dickstein,et al.  Improved generator objectives for GANs , 2016, ArXiv.

[38]  Li Fei-Fei,et al.  Perceptual Losses for Real-Time Style Transfer and Super-Resolution , 2016, ECCV.

[39]  Andrew McCallum,et al.  Structured Prediction Energy Networks , 2015, ICML.

[40]  Yoshua Bengio,et al.  Bidirectional Helmholtz Machines , 2015, ICML.

[41]  Bernt Schiele,et al.  Learning What and Where to Draw , 2016, NIPS.

[42]  Thomas Brox,et al.  Synthesizing the preferred inputs for neurons in neural networks via deep generator networks , 2016, NIPS.

[43]  Alexei A. Efros,et al.  Generative Visual Manipulation on the Natural Image Manifold , 2016, ECCV.

[44]  Sebastian Nowozin,et al.  f-GAN: Training Generative Neural Samplers using Variational Divergence Minimization , 2016, NIPS.

[45]  Samy Bengio,et al.  Density estimation using Real NVP , 2016, ICLR.

[46]  Lucas Theis,et al.  Amortised MAP Inference for Image Super-resolution , 2016, ICLR.

[47]  Max Welling,et al.  Improved Variational Inference with Inverse Autoregressive Flow , 2016, NIPS 2016.

[48]  Tian Han,et al.  Alternating Back-Propagation for Generator Network , 2016, AAAI.

[49]  Christian Ledig,et al.  Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[50]  Jonathon Shlens,et al.  Conditional Image Synthesis with Auxiliary Classifier GANs , 2016, ICML.

[51]  Yoshua Bengio,et al.  Mode Regularized Generative Adversarial Networks , 2016, ICLR.

[52]  Aaron C. Courville,et al.  Adversarially Learned Inference , 2016, ICLR.