Wasserstein proximal operators describe score-based generative models and resolve memorization
CoRR(2024)
摘要
We focus on the fundamental mathematical structure of score-based generative
models (SGMs). We first formulate SGMs in terms of the Wasserstein proximal
operator (WPO) and demonstrate that, via mean-field games (MFGs), the WPO
formulation reveals mathematical structure that describes the inductive bias of
diffusion and score-based models. In particular, MFGs yield optimality
conditions in the form of a pair of coupled partial differential equations: a
forward-controlled Fokker-Planck (FP) equation, and a backward
Hamilton-Jacobi-Bellman (HJB) equation. Via a Cole-Hopf transformation and
taking advantage of the fact that the cross-entropy can be related to a linear
functional of the density, we show that the HJB equation is an uncontrolled FP
equation. Second, with the mathematical structure at hand, we present an
interpretable kernel-based model for the score function which dramatically
improves the performance of SGMs in terms of training samples and training
time. In addition, the WPO-informed kernel model is explicitly constructed to
avoid the recently studied memorization effects of score-based generative
models. The mathematical form of the new kernel-based models in combination
with the use of the terminal condition of the MFG reveals new explanations for
the manifold learning and generalization properties of SGMs, and provides a
resolution to their memorization effects. Finally, our mathematically informed,
interpretable kernel-based model suggests new scalable bespoke neural network
architectures for high-dimensional applications.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要