Unsupervised Minimax: Adversarial Curiosity, Generative Adversarial Networks, and Predictability Minimization

I review unsupervised or self-supervised neural networks playing minimax games in game-theoretic settings. (i) Adversarial Curiosity (AC, 1990) is based on two such networks. One network learns to probabilistically generate 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. We correct a previously published claim that PM is not based on a minimax game.