DeepAI AI Chat
Log In Sign Up

Monge-Ampère Flow for Generative Modeling

by   Linfeng Zhang, et al.
Princeton University

We present a deep generative model, named Monge-Ampère flow, which builds on continuous-time gradient flow arising from the Monge-Ampère equation in optimal transport theory. The generative map from the latent space to the data space follows a dynamical system, where a learnable potential function guides a compressible fluid to flow towards the target density distribution. Training of the model amounts to solving an optimal control problem. The Monge-Ampère flow has tractable likelihoods and supports efficient sampling and inference. One can easily impose symmetry constraints in the generative model by designing suitable scalar potential functions. We apply the approach to unsupervised density estimation of the MNIST dataset and variational calculation of the two-dimensional Ising model at the critical point. This approach brings insights and techniques from Monge-Ampère equation, optimal transport, and fluid dynamics into reversible flow-based generative models.


page 5

page 6


Potential Flow Generator with L_2 Optimal Transport Regularity for Generative Models

We propose a potential flow generator with L_2 optimal transport regular...

OT-Flow: Fast and Accurate Continuous Normalizing Flows via Optimal Transport

A normalizing flow is an invertible mapping between an arbitrary probabi...

Convex Potential Flows: Universal Probability Distributions with Optimal Transport and Convex Optimization

Flow-based models are powerful tools for designing probabilistic models ...

Manifold Interpolating Optimal-Transport Flows for Trajectory Inference

Here, we present a method called Manifold Interpolating Optimal-Transpor...

Learning Implicit Generative Models with Theoretical Guarantees

We propose a unified framework for implicit generative modeling (UnifiGe...

Likelihood Training of Schrödinger Bridge using Forward-Backward SDEs Theory

Schrödinger Bridge (SB) is an optimal transport problem that has receive...

DeepFlow: History Matching in the Space of Deep Generative Models

The calibration of a reservoir model with observed transient data of flu...