Towards Principled Methods for Training Generative Adversarial Networks

Abstract

The goal of this paper is not to introduce a single algorithm or method, but to make theoretical steps towards fully understanding the training dynamics of generative adversarial networks. In order to substantiate our theoretical analysis, we perform targeted experiments to verify our assumptions, illustrate our claims, and quantify the phenomena. This paper is divided into three sections. The first section introduces the problem at hand. The second section is dedicated to studying and proving rigorously the problems including instability and saturation that arize when training generative adversarial networks. The third section examines a practical and theoretically grounded direction towards solving these problems, while introducing new tools to study them.

References in corpus (3)

• Explaining and Harnessing Adversarial Examples
• Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks
• Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling

Cited by in corpus (35)

• Towards the Automatic Anime Characters Creation with Generative Adversarial Networks
• ChemGAN challenge for drug discovery: can AI reproduce natural chemical diversity?
• Model-based Deep Reinforcement Learning for Dynamic Portfolio Optimization
• On denoising autoencoders trained to minimise binary cross-entropy
• Spatial Evolutionary Generative Adversarial Networks
• Tutorial: Deriving the Standard Variational Autoencoder (VAE) Loss Function
• Comparison of Maximum Likelihood and GAN-based training of Real NVPs
• Face Transfer with Generative Adversarial Network
• CnGAN: Generative Adversarial Networks for Cross-network user preference generation for non-overlapped users
• Machine Learning Methods Economists Should Know About
• Neural Language Generation: Formulation, Methods, and Evaluation
• High-Quality Face Image SR Using Conditional Generative Adversarial Networks
• A unified framework for 21cm tomography sample generation and parameter inference with Progressively Growing GANs
• eCommerceGAN : A Generative Adversarial Network for E-commerce
• Training Generative Adversarial Networks by Solving Ordinary Differential Equations
• Fluid Flow Mass Transport for Generative Networks
• An Improved Self-supervised GAN via Adversarial Training
• LGAN: Lung Segmentation in CT Scans Using Generative Adversarial Network
• Metric Learning-based Generative Adversarial Network
• On Relativistic $f$-Divergences
• Artist Style Transfer Via Quadratic Potential
• BasketballGAN: Generating Basketball Play Simulation Through Sketching
• A Generative Model for Hallucinating Diverse Versions of Super Resolution Images
• Efficient Super Resolution For Large-Scale Images Using Attentional GAN
• Classification of sparsely labeled spatio-temporal data through semi-supervised adversarial learning
• Semi-supervised mp-MRI Data Synthesis with StitchLayer and Auxiliary Distance Maximization
• Data-driven Accelerogram Synthesis using Deep Generative Models
• Mode Penalty Generative Adversarial Network with adapted Auto-encoder
• Cross-modal Image Retrieval with Deep Mutual Information Maximization
• Diversity Regularized Adversarial Learning
• A Self-Training Method for Semi-Supervised GANs
• Generic Semi-Supervised Adversarial Subject Translation for Sensor-Based Human Activity Recognition
• Generative Adversarial Learning via Kernel Density Discrimination
• Improving Stability of LS-GANs for Audio and Speech Signals
• On the Performance of Generative Adversarial Network (GAN) Variants: A Clinical Data Study