Problem
Research questions and friction points this paper is trying to address.
score-matching diffusion models
convolutional architecture
effective field theory
information spreading
Information Spreading in Diffusion Models from Effective Field Theory
🤖 AI Summary
研究利用有效场理论方法分析卷积架构下的分数匹配扩散模型，解决信息传播问题，并通过MNIST等实例验证了该方法的有效性。
📝 Abstract
We study score-matching diffusion models with a convolutional architecture. We argue that the inductive bias of locality means that the machinery of effective field theory from physics can be usefully applied to describe the denoising dynamics. We apply this formalism first to a simple toy example which permits an analytical description, and thereafter to MNIST, and show that in both cases, the mutual information between two points grows in a manner predicted by a simple effective field theory of Brownian motion.
Innovation
Methods, ideas, or system contributions that make the work stand out.
effective field theory
score-matching diffusion models
mutual information
🔎 Similar Papers
No similar papers found.
