They show that for Bernoulli noise on the hypercube, the score of the noisy distribution gives the optimal Hamming denoiser, and they prove Wasserstein convergence for two discrete Langevin samplers at high noise.
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
-
Sampling Binary Data by Denoising through Score Functions
They show that for Bernoulli noise on the hypercube, the score of the noisy distribution gives the optimal Hamming denoiser, and they prove Wasserstein convergence for two discrete Langevin samplers at high noise.