Showing 2023Show all
2 papers · 1 filter
math.NA2023
Discrete-to-Continuum Rates of Convergence for -Laplacian Regularization
Adrien Weihs, Jalal Fadili, Matthew Thorpe
Higher-order regularization problem formulations are popular frameworks used in machine learning, inverse problems and image/signal processing. In this paper, we consider the compu…
math.ST2023
Consistency of Fractional Graph-Laplacian Regularization in Semi-Supervised Learning with Finite Labels
Adrien Weihs, Matthew Thorpe
Laplace learning is a popular machine learning algorithm for finding missing labels from a small number of labelled feature vectors using the geometry of a graph. More precisely, L…