1,A number of works (Ue-hara et al., 2016; Qi, 2017; Gulrajani et al., 2017) advocate the importance of Lipschitz continuity in assuring the boundedness of statistics
1.1 Ue-hara et al., 2016;Generative Adversarial Nets from a Density Ratio Estimation Perspective
1.1.1 density ratio estimation
Divergence estimation and two-sample homogeneity test under semiparametric density-ratio models
1.1.1.1 semiparametric density ratio estimator;
semiparametric density ratio estimator
1.1.1.1.1 K b (?) ¼ b ?1 K(?=b)
Density Estimation for Statistics and Data Analysis
2,W-GAN
2.1 It is then unlikely that the model manifold and the true distribution’s support have a non-negligible intersection
T OWARDS P RINCIPLED M ETHODS FOR T RAINING GENERATIVE A DVERSARIAL N ETWORKS
2.1.1 One possible cause for the distributions not to be continuous is if their supports lie on low dimen-
sional manifolds. There is strong empirical and theoretical evidence to believe that P r is indeed
extremely concentrated on a low dimensional manifold
Optimal Transport: Old and New