CDS combines parallel tempering for initial exploration with exact diffusion transport via conditional interpolants to sample unnormalized multimodal distributions more efficiently.
Then, the conditional distributionν t|z converges to the Dirac massδ z in the Wasserstein-1 distance: lim t→0 W1(δz, νt|z) = 0,(42) Proof
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Conditional Diffusion Sampling
CDS combines parallel tempering for initial exploration with exact diffusion transport via conditional interpolants to sample unnormalized multimodal distributions more efficiently.