Generative Adversarial Networks are Special Cases of Artificial Curiosity (1990) and also Closely Related to Predictability Minimization (1991)
arXiv:1906.04493
Abstract
I review unsupervised or self-supervised neural networks playing minimax games in game-theoretic settings: (i) Artificial Curiosity (AC, 1990) is based on two such networks. One network learns to generate a probability distribution over outputs, the other learns to predict effects of the outputs. Each network minimizes the objective function maximized by the other. (ii) Generative Adversarial Networks (GANs, 2010-2014) are an application of AC where the effect of an output is 1 if the output is in a given set, and 0 otherwise. (iii) Predictability Minimization (PM, 1990s) models data distributions through a neural encoder that maximizes the objective function minimized by a neural predictor of the code components. I correct a previously published claim that PM is not based on a minimax game.
arXiv comment15 pages, 1 figure, 104 references
References in corpus (19)
- Deep Learning in Neural Networks: An Overview
- Conditional Generative Adversarial Nets
- Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
- GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
- Stochastic Backpropagation and Approximate Inference in Deep Generative Models
- The information bottleneck method
- InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets
- Adversarially Learned Inference
- Domain Separation Networks
- A Neural Representation of Sketch Drawings
- How (not) to Train your Generative Model: Scheduled Sampling, Likelihood, Adversary?
- Synthesizing Programs for Images using Reinforced Adversarial Learning
- Convergence rate of linear two-time-scale stochastic approximation
- Connecting Generative Adversarial Networks and Actor-Critic Methods
- On Finding Local Nash Equilibria (and Only Local Nash Equilibria) in Zero-Sum Games
- Learning to Paint With Model-based Deep Reinforcement Learning
- On Learning to Think: Algorithmic Information Theory for Novel Combinations of Reinforcement Learning Controllers and Recurrent Neural World Models
- Neural Painters: A learned differentiable constraint for generating brushstroke paintings
- One Big Net For Everything