S-MEME iteratively fine-tunes a diffusion model using its own score as the exploration reward, provably converging to the maximum-entropy distribution on the learned manifold.
Mirror descent with relative smoothness in measure spaces, with application to sinkhorn and em
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Provable Maximum Entropy Manifold Exploration via Diffusion Models
S-MEME iteratively fine-tunes a diffusion model using its own score as the exploration reward, provably converging to the maximum-entropy distribution on the learned manifold.