activity
20122022
most citedSmallest Gaps Between Eigenvalues of Random Matrices With Complex Ginibre, Wishart and Universal Unitary Ensembles

5 citations · 7 across the 5 of their papers we have counts for

collaborators

5 papers

cs.LG20222 cited

Generalized energy and gradient flow via graph framelets

Andi Han, Dai Shi, Zhiqi Shao +1

In this work, we provide a theoretical understanding of the framelet-based graph neural networks through the perspective of energy gradient flow. By viewing the framelet-based mode…

cs.LG2021

A Discussion On the Validity of Manifold Learning

Dai Shi, Andi Han, Yi Guo +1

Dimensionality reduction (DR) and manifold learning (ManL) have been applied extensively in many machine learning tasks, including signal processing, speech recognition, and neuroi…

cs.LG2019

Coupling Matrix Manifolds and Their Applications in Optimal Transport

Dai Shi, Junbin Gao, Xia Hong +2

Optimal transport (OT) is a powerful tool for measuring the distance between two defined probability distributions. In this paper, we develop a new manifold named the coupling matr…

math.PR2012

Asymptotic Joint Distribution of Extreme Eigenvalues of the Sample Covariance Matrix in the Spiked Population Model

Dai Shi

In this paper, we consider a data matrix where all the columns are i.i.d. samples being dimensional complex Gaussian of mean zero and covariance $Σ…

math.PR20125 cited

Smallest Gaps Between Eigenvalues of Random Matrices With Complex Ginibre, Wishart and Universal Unitary Ensembles

Dai Shi, Yunjiang Jiang

In this paper we study the limiting distribution of the smallest gaps between eigenvalues of three kinds of random matrices -- the Ginibre ensemble, the Wishart ensemble and th…