Glossary term
Glossary term
Evaluation and Benchmarks
A loss function for generative adversarial networks, based on the cross-entropy between the distribution of generated data and real data.
Minimax loss is used in the first paper to describe generative adversarial networks.
See Loss Functions in the Generative Adversarial Networks course for more information.
Created for this library
A research team uses minimax loss in its original GAN setup to train the generator and discriminator against each other.
A research lab uses minimax loss as the starting point when teaching GANs before introducing more stable variants.
An ML team studies minimax loss as the baseline for understanding GAN training dynamics before applying alternatives.
Definition source: Google for Developers Machine Learning Glossary | Creative Commons Attribution 4.0 License