Nonparametric Density Estimation under Adversarial Losses
NeurIPS, pp. 10225-10236, 2018.
total variation distancegenerative adversarial networkswasserstein distance
We study minimax convergence rates of nonparametric density estimation under a large class of loss functions called ``adversarial lossesu0027u0027, which, besides classical L^p losses, includes maximum mean discrepancy (MMD), Wasserstein distance, and total variation distance. These losses are closely related to the losses encoded by disc...More