#machine learning
Jul 2026
Missing Data Imputation under Manifold Hypothesis
This work proposes a model-based imputation method that enables sampling from p via a sampling-importance-resampling (SIR) procedure, which can be further augmented with a joint diffusion model in the latent space, and achieves competitive performance compared to state-of-the-art procedures.
Z. Bi, Amuche Ibenegbu, S. Moka
· arXiv.org · 0 citations