For arbitrary data distributions, classifier-free guidance provably decreases the expected reciprocal classifier probability along the reverse diffusion process.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Provable Efficiency of Guidance in Diffusion Models for General Data Distribution
For arbitrary data distributions, classifier-free guidance provably decreases the expected reciprocal classifier probability along the reverse diffusion process.