534 citations · 2k across the 96 of their papers we have counts for
4 papers · 2 filters
Spectral Convergence of Graph Laplacian and Heat Kernel Reconstruction in from Random Samples
David B Dunson, Hau-Tieng Wu, Nan Wu
In the manifold setting, we provide a series of spectral convergence results quantifying how the eigenvectors and eigenvalues of the graph Laplacian converge to the eigenfunctions…
On the spectral property of kernel-based sensor fusion algorithms of high dimensional data
Xiucai Ding, Hau-Tieng Wu
We apply local laws of random matrices and free probability theory to study the spectral properties of two kernel-based sensor fusion algorithms, nonparametric canonical correlatio…
Asymptotic analysis of synchrosqueezing transform -- toward statistical inference with nonlinear-type time-frequency analysis
Matt Sourisseau, Hau-Tieng Wu, Zhou Zhou
We provide a statistical analysis of a tool in nonlinear-type time-frequency analysis, the synchrosqueezing transform (SST), for both the null and non-null cases. The intricate non…
Optimal Recovery of Precision Matrix for Mahalanobis Distance from High Dimensional Noisy Observations in Manifold Learning
Matan Gavish, Ronen Talmon, Pei-Chun Su +1
Motivated by establishing theoretical foundations for various manifold learning algorithms, we study the problem of Mahalanobis distance (MD), and the associated precision matrix,…