26 citations · 136 across the 23 of their papers we have counts for
23 papers
Spectral Concentration and Recovery in Sparse High-Dimensional Random Geometric Graphs
Manuel Fernandez, Yizhe Zhu
We study sparse threshold random geometric graphs generated by high-dimensional spherical or Gaussian latent vectors. Although each edge has marginal probability , shared latent…
Spectral gap-based deterministic tensor completion
Kameron Decker Harris, Oscar López, Angus Read +1
Tensor completion is a core machine learning algorithm used in recommender systems and other domains with missing data. While the matrix case is well-understood, theoretical result…
A non-backtracking method for long matrix and tensor completion
Ludovic Stephan, Yizhe Zhu
We consider the problem of low-rank rectangular matrix completion in the regime where the matrix of size is ``long", i.e., the aspect ratio diverges to infini…
Algorithmically Effective Differentially Private Synthetic Data
Yiyun He, Roman Vershynin, Yizhe Zhu
We present a highly effective algorithmic approach for generating -differentially private synthetic data in a bounded metric space with near-optimal utility guarantees…
Overparameterized random feature regression with nearly orthogonal data
Zhichao Wang, Yizhe Zhu
We investigate the properties of random feature ridge regression (RFRR) given by a two-layer neural network with random Gaussian initialization. We study the non-asymptotic behavio…
Extreme singular values of inhomogeneous sparse random rectangular matrices
Ioana Dumitriu, Yizhe Zhu
We develop a unified approach to bounding the largest and smallest singular values of an inhomogeneous random rectangular matrix, based on the non-backtracking operator and the Iha…
Robust recovery of low-rank matrices and low-tubal-rank tensors from noisy sketches
Anna Ma, Dominik Stöger, Yizhe Zhu
A common approach for compressing large-scale data is through matrix sketching. In this work, we consider the problem of recovering low-rank matrices from two noisy linear sketches…
The characteristic polynomial of sums of random permutations and regular digraphs
Simon Coste, Gaultier Lambert, Yizhe Zhu
Let be the sum of permutation matrices of size , each drawn uniformly at random and independently. We prove that the normalized characteristic polynomial $\fra…
Sparse random hypergraphs: Non-backtracking spectra and community detection
Ludovic Stephan, Yizhe Zhu
We consider the community detection problem in a sparse -uniform hypergraph , assuming that is generated according to the Hypergraph Stochastic Block Model (HSBM). We pro…
Sparse recovery properties of discrete random matrices
Asaf Ferber, Ashwin Sah, Mehtaab Sawhney +1
Motivated by problems from compressed sensing, we determine the threshold behavior of a random matrix with respect to the property "every columns…
Partial recovery and weak consistency in the non-uniform hypergraph Stochastic Block Model
Ioana Dumitriu, Hai-Xiao Wang, Yizhe Zhu
We consider the community detection problem in sparse random hypergraphs under the non-uniform hypergraph stochastic block model (HSBM), a general model of random networks with com…
Deformed semicircle law and concentration of nonlinear random matrices for ultra-wide neural networks
Zhichao Wang, Yizhe Zhu
In this paper, we investigate a two-layer fully connected neural network of the form , where $X\in\mathbb{R}^{d_0\tim…
Global eigenvalue fluctuations of random biregular bipartite graphs
Ioana Dumitriu, Yizhe Zhu
We compute the eigenvalue fluctuations of uniformly distributed random biregular bipartite graphs with fixed and growing degrees for a large class of analytic functions. As a key s…
On the second eigenvalue of random bipartite biregular graphs
Yizhe Zhu
We consider the spectral gap of a uniformly chosen random -biregular bipartite graph with , where could possibly grow with and . L…
Asymptotic Behavior of a Sequence of Conditional Probability Distributions and the Canonical Ensemble
Yu-Chen Cheng, Hong Qian, Yizhe Zhu
The probability distribution of a function of a subsystem conditioned on the value of the function of the whole, in the limit when the ratio of their values goes to zero, has a lim…
Sparse random tensors: Concentration, regularization and applications
Zhixin Zhou, Yizhe Zhu
We prove a non-asymptotic concentration inequality for the spectral norm of sparse inhomogeneous random tensors with Bernoulli entries. For an order- inhomogeneous random tensor…
Deterministic tensor completion with hypergraph expanders
Kameron Decker Harris, Yizhe Zhu
We provide a novel analysis of low-rank tensor completion based on hypergraph expanders. As a proxy for rank, we minimize the max-quasinorm of the tensor, which generalizes the max…
Eigenvalues of the non-backtracking operator detached from the bulk
Simon Coste, Yizhe Zhu
We describe the non-backtracking spectrum of a stochastic block model with connection probabilities . In this regime we answer a qu…
Spectra of random regular hypergraphs
Ioana Dumitriu, Yizhe Zhu
In this paper, we study the spectra of regular hypergraphs following the definitions from Feng and Li (1996). Our main result is an analog of Alon's conjecture for the spectral gap…
Community detection in the sparse hypergraph stochastic block model
Soumik Pal, Yizhe Zhu
We consider the community detection problem in sparse random hypergraphs. Angelini et al. (2015) conjectured the existence of a sharp threshold on model parameters for community de…
Exact Recovery in the Hypergraph Stochastic Block Model: a Spectral Algorithm
Sam Cole, Yizhe Zhu
We consider the exact recovery problem in the hypergraph stochastic block model (HSBM) with blocks of equal size. More precisely, we consider a random -uniform hypergraph $H…
Sparse General Wigner-type Matrices: Local Law and Eigenvector Delocalization
Ioana Dumitriu, Yizhe Zhu
We prove a local law and eigenvector delocalization for general Wigner-type matrices. Our methods allow us to get the best possible interval length and optimal eigenvector delocali…
A Graphon Approach to Limiting Spectral Distributions of Wigner-type Matrices
Yizhe Zhu
We present a new approach, based on graphon theory, to finding the limiting spectral distributions of general Wigner-type matrices. This approach determines the moments of the limi…