Analyzing Neural Network-Based Generative Diffusion Models through Convex Optimization
This work offers a theoretical foundation for understanding what neural networks learn in diffusion models, which is incremental but precise for researchers in generative AI.
The authors tackled the problem of analyzing neural network-based diffusion models by reframing score matching as convex optimization, proving that training shallow networks for score prediction can be done via a single convex program and providing exact characterizations and convergence results with finite data.
Diffusion models are gaining widespread use in cutting-edge image, video, and audio generation. Score-based diffusion models stand out among these methods, necessitating the estimation of score function of the input data distribution. In this study, we present a theoretical framework to analyze two-layer neural network-based diffusion models by reframing score matching and denoising score matching as convex optimization. We prove that training shallow neural networks for score prediction can be done by solving a single convex program. Although most analyses of diffusion models operate in the asymptotic setting or rely on approximations, we characterize the exact predicted score function and establish convergence results for neural network-based diffusion models with finite data. Our results provide a precise characterization of what neural network-based diffusion models learn in non-asymptotic settings.