Open NicolaBernini opened 3 years ago
GANs require solving an optimization problem which is harder than the single objective optimization problem typically observed in current ML: it is a MinMax optimization problem, so it combines multiple objectives, the ones of the 2 adversarial players
Using the usual tools, i.e. gradient based methods, works in theory but practically there are problems in terms of convergence:
Analysis of the paper
Generative Minimization Networks: Training GANs Without Competition
https://arxiv.org/abs/2103.12685v1