Deep Generative Learning via Schrödinger Bridge

06/19/2021
by   Gefei Wang, et al.
48

We propose to learn a generative model via entropy interpolation with a Schrödinger Bridge. The generative learning task can be formulated as interpolating between a reference distribution and a target distribution based on the Kullback-Leibler divergence. At the population level, this entropy interpolation is characterized via an SDE on [0,1] with a time-varying drift term. At the sample level, we derive our Schrödinger Bridge algorithm by plugging the drift term estimated by a deep score estimator and a deep density ratio estimator into the Euler-Maruyama method. Under some mild smoothness assumptions of the target distribution, we prove the consistency of both the score estimator and the density ratio estimator, and then establish the consistency of the proposed Schrödinger Bridge approach. Our theoretical results guarantee that the distribution learned by our approach converges to the target distribution. Experimental results on multimodal synthetic data and benchmark data support our theoretical findings and indicate that the generative model via Schrödinger Bridge is comparable with state-of-the-art GANs, suggesting a new formulation of generative learning. We demonstrate its usefulness in image interpolation and image inpainting.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 5

page 7

page 8

02/07/2020

Learning Implicit Generative Models with Theoretical Guarantees

We propose a unified framework for implicit generative modeling (UnifiGe...
12/11/2020

Generative Learning With Euler Particle Transport

We propose an Euler particle transport (EPT) approach for generative lea...
01/24/2019

Deep Generative Learning via Variational Gradient Flow

We propose a general framework to learn deep generative models via Varia...
10/19/2021

A Deep Generative Approach to Conditional Sampling

We propose a deep generative approach to sampling from a conditional dis...
01/20/2019

Data Interpolations in Deep Generative Models under Non-Simply-Connected Manifold Topology

Exploiting the deep generative model's remarkable ability of learning th...
06/01/2021

Diffusion Schrödinger Bridge with Applications to Score-Based Generative Modeling

Progressively applying Gaussian noise transforms complex data distributi...
03/27/2021

Particle Filter Bridge Interpolation

Auto encoding models have been extensively studied in recent years. They...

Code Repositories

DGLSB

Deep Generative Learning via Schrödinger Bridge


view repo
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.