2 papers
cs.LG2025
Fast, Accurate Manifold Denoising by Tunneling Riemannian Optimization
Shiyu Wang, Mariam Avagyan, Yihan Shen +5
Learned denoisers play a fundamental role in various signal generation (e.g., diffusion models) and reconstruction (e.g., compressed sensing) architectures, whose success derives f…
stat.ML2025
Local Averaging Accurately Distills Manifold Structure From Noisy Data
Yihan Shen, Shiyu Wang, Arnaud Lamy +2
High-dimensional data are ubiquitous, with examples ranging from natural images to scientific datasets, and often reside near low-dimensional manifolds. Leveraging this geometric s…