AI RESEARCH
C$^2$FG: Control Classifier-Free Guidance via Score Discrepancy Analysis
arXiv CS.LG
•
ArXi:2603.08155v1 Announce Type: new Classifier-Free Guidance (CFG) is a cornerstone of modern conditional diffusion models, yet its reliance on the fixed or heuristic dynamic guidance weight is predominantly empirical and overlooks the inherent dynamics of the diffusion process. In this paper, we provide a rigorous theoretical analysis of the Classifier-Free Guidance. Specifically, we establish strict upper bounds on the score discrepancy between conditional and unconditional distributions at different timesteps based on the diffusion process.