A mean-field games laboratory for generative modeling

04/26/2023
by   Benjamin J. Zhang, et al.
0

In this paper, we demonstrate the versatility of mean-field games (MFGs) as a mathematical framework for explaining, enhancing, and designing generative models. There is a pervasive sense in the generative modeling community that the various flow and diffusion-based generative models have some common foundational structure and interrelationships. We establish connections between MFGs and major classes of flow and diffusion-based generative models including continuous-time normalizing flows, score-based models, and Wasserstein gradient flows. We derive these three classes of generative models through different choices of particle dynamics and cost functions. Furthermore, we study the mathematical structure and properties of each generative model by studying their associated MFG's optimality condition, which is a set of coupled forward-backward nonlinear partial differential equations (PDEs). The theory of MFGs, therefore, enables the study of generative models through the theory of nonlinear PDEs. Through this perspective, we investigate the well-posedness and structure of normalizing flows, unravel the mathematical structure of score-based generative modeling, and derive a mean-field game formulation of the Wasserstein gradient flow. From an algorithmic perspective, the optimality conditions of MFGs also allow us to introduce HJB regularizers for enhanced training of a broad class of generative models. In particular, we propose and demonstrate an Hamilton-Jacobi-Bellman regularized SGM with improved performance over standard SGMs. We present this framework as an MFG laboratory which serves as a platform for revealing new avenues of experimentation and invention of generative models. This laboratory will give rise to a multitude of well-posed generative modeling formulations and will provide a consistent theoretical framework upon which numerical and algorithmic tools may be developed.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
03/09/2020

Mean Field Games and Applications: Numerical Aspects

The theory of mean field games aims at studying deterministic or stochas...
research
04/05/2023

GenPhys: From Physical Processes to Generative Models

Since diffusion models (DM) and the more recent Poisson flow generative ...
research
02/09/2023

Geometry of Score Based Generative Models

In this work, we look at Score-based generative models (also called diff...
research
06/30/2022

Bridging Mean-Field Games and Normalizing Flows with Trajectory Regularization

Mean-field games (MFGs) are a modeling framework for systems with a larg...
research
05/03/2023

Nonparametric Generative Modeling with Conditional and Locally-Connected Sliced-Wasserstein Flows

Sliced-Wasserstein Flow (SWF) is a promising approach to nonparametric g...
research
06/17/2022

A Flexible Diffusion Model

Diffusion (score-based) generative models have been widely used for mode...
research
06/24/2021

Distilling the Knowledge from Normalizing Flows

Normalizing flows are a powerful class of generative models demonstratin...

Please sign up or login with your details

Forgot password? Click here to reset