A Tale of Two Flows: Cooperative Learning of Langevin Flow and Normalizing Flow Toward Energy-Based Model

by   Jianwen Xie, et al.

This paper studies the cooperative learning of two generative flow models, in which the two models are iteratively updated based on the jointly synthesized examples. The first flow model is a normalizing flow that transforms an initial simple density to a target density by applying a sequence of invertible transformations. The second flow model is a Langevin flow that runs finite steps of gradient-based MCMC toward an energy-based model. We start from proposing a generative framework that trains an energy-based model with a normalizing flow as an amortized sampler to initialize the MCMC chains of the energy-based model. In each learning iteration, we generate synthesized examples by using a normalizing flow initialization followed by a short-run Langevin flow revision toward the current energy-based model. Then we treat the synthesized examples as fair samples from the energy-based model and update the model parameters with the maximum likelihood learning gradient, while the normalizing flow directly learns from the synthesized examples by maximizing the tractable likelihood. Under the short-run non-mixing MCMC scenario, the estimation of the energy-based model is shown to follow the perturbation of maximum likelihood, and the short-run Langevin flow and the normalizing flow form a two-flow generator that we call CoopFlow. We provide an understating of the CoopFlow algorithm by information geometry and show that it is a valid generator as it converges to a moment matching estimator. We demonstrate that the trained CoopFlow is capable of synthesizing realistic images, reconstructing images, and interpolating between images.


page 7

page 8

page 9

page 17

page 18


On Learning Non-Convergent Short-Run MCMC Toward Energy-Based Model

This paper studies a curious phenomenon in learning energy-based model (...

Flow Contrastive Estimation of Energy-Based Models

This paper studies a training method to jointly estimate an energy-based...

Learning Energy-based Model with Flow-based Backbone by Neural Transport MCMC

Learning energy-based model (EBM) requires MCMC sampling of the learned ...

On the Anatomy of MCMC-based Maximum Likelihood Learning of Energy-Based Models

This study investigates the effects Markov Chain Monte Carlo (MCMC) samp...

How to Construct Energy for Images? Denoising Autoencoder Can Be Energy Based Model

Energy-based models parameterize the unnormalized log-probability of dat...

Cooperative Training of Descriptor and Generator Networks

This paper studies the cooperative training of two probabilistic models ...

Generalizing Energy-based Generative ConvNets from Particle Evolution Perspective

Compared with Generative Adversarial Networks (GAN), the Energy-Based ge...

Please sign up or login with your details

Forgot password? Click here to reset