Learning Implicit Generative Models with Theoretical Guarantees

Abstract

We propose a \textbf{uni}fied \textbf{f}ramework for \textbf{i}mplicit \textbf{ge}nerative \textbf{m}odeling (UnifiGem) with theoretical guarantees by integrating approaches from optimal transport, numerical ODE, density-ratio (density-difference) estimation and deep neural networks. First, the problem of implicit generative learning is formulated as that of finding the optimal transport map between the reference distribution and the target distribution, which is characterized by a totally nonlinear Monge-Ampère equation. Interpreting the infinitesimal linearization of the Monge-Ampère equation from the perspective of gradient flows in measure spaces leads to the continuity equation or the McKean-Vlasov equation. We then solve the McKean-Vlasov equation numerically using the forward Euler iteration, where the forward Euler map depends on the density ratio (density difference) between the distribution at current iteration and the underlying target distribution. We further estimate the density ratio (density difference) via deep density-ratio (density-difference) fitting and derive explicit upper bounds on the estimation error. Experimental results on both synthetic datasets and real benchmark datasets support our theoretical findings and demonstrate the effectiveness of UnifiGem.

References in corpus (15)

• Auto-Encoding Variational Bayes
• GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
• Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks
• Generative Adversarial Text to Image Synthesis
• Variational Inference with Normalizing Flows
• Generative Moment Matching Networks
• Adversarial Autoencoders
• Learning in Implicit Generative Models
• Generative Models and Model Criticism via Optimized Maximum Mean Discrepancy
• Amortised MAP Inference for Image Super-resolution
• Sliced-Wasserstein Autoencoder: An Embarrassingly Simple Generative Model
• Monge-Ampère Flow for Generative Modeling
• Continuous-Time Flows for Efficient Inference and Density Estimation
• Sinkhorn AutoEncoders
• Wasserstein-Wasserstein Auto-Encoders

Cited by in corpus (3)

• Deep Dimension Reduction for Supervised Representation Learning
• Refining Deep Generative Models via Discriminator Gradient Flow
• Tessellated Wasserstein Auto-Encoders