Introduces tangential Bayes denoiser for Riemannian Gaussian mixtures on manifolds via spectral Laplace-Beltrami approximation, with nearly Bayes risk in low noise and minimax optimality on the circle.
Minimax estimation of sharp change points
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4verdicts
UNVERDICTED 4representative citing papers
Sobolev-ball constraints on the hypothesis class achieve minimax rates for score estimation on the torus and, under conjecture, for generative modeling.
Develops and compares consistent estimators for gradual change points in nonparametric regression using a new optimization method targeting the largest minimization point of an objective function, with rates, regression estimation, bootstrap, and two-sample extensions.
Established mathematical bottlenecks in representation, optimization, complexity, and high-dimensional learning aligned with the central disappointments of early AI research periods.
citing papers explorer
-
Nonparametric Riemannian Empirical Bayes, and Denoising Measurements on Manifolds
Introduces tangential Bayes denoiser for Riemannian Gaussian mixtures on manifolds via spectral Laplace-Beltrami approximation, with nearly Bayes risk in low noise and minimax optimality on the circle.
-
Optimal score function estimation via derivatives constraints
Sobolev-ball constraints on the hypothesis class achieve minimax rates for score estimation on the torus and, under conjecture, for generative modeling.
-
Analysis of gradual changes in nonparametric regression based on a new optimization method in the non-unique case
Develops and compares consistent estimators for gradual change points in nonparametric regression using a new optimization method targeting the largest minimization point of an objective function, with rates, regression estimation, bootstrap, and two-sample extensions.
-
The Mathematics of AI Winters: The mathematical Taxonomy of Paradigm Fragility in AI Winter
Established mathematical bottlenecks in representation, optimization, complexity, and high-dimensional learning aligned with the central disappointments of early AI research periods.