A convex-relaxation denoiser projects PCA-reduced noisy manifold data onto the convex hull using a Gaussian-tail oracle, with finite-sample error bounds under a lower-mass condition on the latent distribution.
Fitting a manifold to data in the presence of large noise
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
An efficient algorithm reconstructs manifold geometry from random geometric graphs under the manifold assumption with distance-dependent connection probabilities.
citing papers explorer
-
Denoising data using convex relaxations
A convex-relaxation denoiser projects PCA-reduced noisy manifold data onto the convex hull using a Gaussian-tail oracle, with finite-sample error bounds under a lower-mass condition on the latent distribution.
-
Reconstructing the Geometry of Random Geometric Graphs
An efficient algorithm reconstructs manifold geometry from random geometric graphs under the manifold assumption with distance-dependent connection probabilities.