arXiv (Cornell University) · 2018 · 23 citations · 25 references
ComputingComputer ScienceMachine LearningOptimizationStatistical LearningDeep LearningDensity EstimationGenerative ModelingLoss FunctionNeural NetworksOptimization For Machine LearningAdversarial LossGenerative Adversarial NetworksImplicit Generative ModelsMinimax OptimizationMinimax RatesNonparametric Density EstimationNonparametric EstimationTotal Variation Minimization
We study minimax convergence rates of nonparametric density estimation under a large class of loss functions called "adversarial losses", which, besides classical $\mathcal{L}^p$ losses, includes maximum mean discrepancy (MMD), Wasserstein distance, and total variation distance. These losses are closely related to the losses encoded by discriminator networks in generative adversarial networks (GANs). In a general framework, we study how the choice of loss and the assumed smoothness of the underlying density together determine the minimax rate. We also discuss implications for training GANs based on deep ReLU networks, and more general connections to learning implicit generative models in a minimax statistical sense.
25
Auto-Encoding Variational Bayes
Diederik P. Kingma, Max Welling · UvA-DARE (University of Amsterdam) · 2013 · 15.6K citations · Full text
Arthur Gretton, Karsten Borgwardt, Malte J. Rasch et al. · MPG.PuRe (Max Planck Society) · 2012 · 2.2K citations · Full text
Improved Training of Wasserstein GANs
Ishaan Gulrajani, Faruk Ahmed, Martín Arjovsky et al. · arXiv (Cornell University) · 2017 · 1.5K citations · Full text