Nonparametric Density Estimation under Adversarial Losses

    NeurIPS, pp. 10225-10236, 2018.

    Cited by: 15|Bibtex|Views9|Links
    EI
    Keywords:
    total variation distancegenerative adversarial networkswasserstein distance

    Abstract:

    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

    Code:

    Data:

    Your rating :
    0

     

    Tags
    Comments