A provably convergent gradient descent that estimates a data manifold from a point cloud and stays near it during optimization, applied to learned operator correction in inverse problems.
Approximation errors and model reduction with an application in optical diffusion tomography
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
math.NA 1years
2026 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Gradient Descent on Point Clouds and Applications in Learned Operator Correction
A provably convergent gradient descent that estimates a data manifold from a point cloud and stays near it during optimization, applied to learned operator correction in inverse problems.