Learning Implicit Generative Models Using Differentiable Graph Tests

@article{Djolonga2017LearningIG,
  title={Learning Implicit Generative Models Using Differentiable Graph Tests},
  author={Josip Djolonga and Andreas Krause},
  journal={CoRR},
  year={2017},
  volume={abs/1709.01006}
}
Recently, there has been a growing interest in the problem of learning rich implicit models — those from which we can sample, but can not evaluate their density. These models apply some parametric function, such as a deep network, to a base measure, and are learned end-to-end using stochastic optimization. One strategy of devising a loss function is through the statistics of two sample tests — if we can fool a statistical test, the learned distribution should be a good model of the true data… CONTINUE READING