Research

Publications

Preprints and papers in probability, statistics, and mathematical foundations of learning.

An asterisk (*) denotes an undergraduate research project.

Preprints

Concentration of bounded sparse chaoses and sparse Khatri-Rao embeddings
with Guozheng Dai, Yiyun He, and Ke Wang, submitted, 2026.
arXiv
Sharp spectral norm concentration and regularization of sparse random tensors
with Zhixin Zhou, 2026.
arXiv
The spectral edge of sparse directed Erdős–Rényi graphs
with Simon Coste, 2026.
arXiv
Spectral concentration and recovery in sparse high-dimensional random geometric graphs
with Manuel Fernandez, submitted, 2026.
arXiv
Achieving the Kesten-Stigum bound in the non-uniform hypergraph stochastic block model
with Manuel Fernandez and Ludovic Stephan, submitted, 2026.
arXiv
Power-law spectrum of the random feature model
with Elliot Paquette and Ke Liang Xiao, submitted, 2026.
arXiv
Singular values of sparse random rectangular matrices: Emergence of outliers at criticality
with Ioana Dumitriu, Haixiao Wang, and Zhichao Wang, submitted, 2025.
arXiv
Spectra of high-dimensional sparse random geometric graphs^*
with Yifan Cao, submitted, 2025.
arXiv
A note on the improved sparse Hanson-Wright inequalities
with Guozheng Dai, Yiyun He, and Ke Wang, submitted, 2025.
arXiv
Central limit theorems for linear spectral statistics of inhomogeneous random graphs with graphon limits^*
with Xiangyi Zhu, submitted, 2024.
arXiv

Papers

Non-backtracking eigenvalues and eigenvectors of random regular graphs and hypergraphs^*
with Xiangyi Zhu, Discrete Mathematics, to appear.
arXiv
A semicircle law for the normalized Laplacian of sparse random graphs
with Yiming Chen and Zijun Chen, Bernoulli, to appear.
arXiv
Wedge sampling: Efficient tensor completion with nearly-linear sample complexity
with Hengrui Luo, Anna Ma, and Ludovic Stephan, COLT 2026.
arXiv
Minimax optimal differentially private synthetic data for smooth queries
with Rundong Ding and Yiyun He, COLT 2026.
arXiv
Regular bipartite decompositions of pseudorandom graphs
with Asaf Ferber, Bryce Frederickson, Dingjia Mao, and Liana Yepremyan, Journal of Combinatorial Theory, Series B, 179, 270-292,2026.
arXiv Journal
Sparse Hanson-Wright inequalities with applications
with Yiyun He and Ke Wang, Electronic Journal of Probability, 31:1-49, 2026.
arXiv Journal
Universality of kernel random matrices and kernel regression in the quadratic regime
with Parthe Pandit and Zhichao Wang, Journal of Machine Learning Research, 26(224):1-73,2025.
arXiv Journal
Community detection with the Bethe-Hessian
with Ludovic Stephan, COLT 2025.
arXiv
Non-convex matrix sensing: Breaking the quadratic rank barrier in the sample complexity
with Dominik Stöger, COLT 2025.
arXiv
Differentially private low-dimensional synthetic data from high-dimensional datasets
with Yiyun He, Thomas Strohmer, and Roman Vershynin, Information and Inference, 14(1), iaae034, 2025.
arXiv Journal
Partial recovery and weak consistency in the non-uniform hypergraph stochastic block model
with Ioana Dumitriu and Haixiao Wang, Combinatorics, Probability and Computing, 34(1), 1-51, 2025.
arXiv Journal
Online differentially private synthetic data generation
with Yiyun He and Roman Vershynin, IEEE Transactions on Privacy, 1(1): 19-30, 2024.
arXiv Journal
Extreme singular values of inhomogeneous sparse random rectangular matrices
with Ioana Dumitriu, Bernoulli, 30(4): 2904-2931, 2024.
arXiv Journal
A non-backtracking method for long matrix and tensor completion
with Ludovic Stephan, Proceedings of Thirty Seventh Conference on Learning Theory (COLT), PMLR 247:4636-4690, 2024.
arXiv Conference proceedings
Deformed semicircle law and concentration of nonlinear random matrices for ultra-wide neural networks
with Zhichao Wang, Annals of Applied Probability, 34(2), 1896-1947, 2024.
arXiv Journal
Sparse random hypergraphs: Non-backtracking spectra and community detection
with Ludovic Stephan, Information and Inference, 13(1), iaae004, 2024. Conference version in FOCS 2022.
arXiv Journal Conference proceedings
The characteristic polynomial of sums of random permutations and regular digraphs
with Simon Coste and Gaultier Lambert, International Mathematics Research Notices, 2024(3), 2461-2510, 2024.
arXiv Journal
Robust recovery of low-rank matrices and low-tubal-rank tensors from noisy sketches
with Anna Ma and Dominik Stöger, SIAM Journal on Matrix Analysis and Applications, 44 (4), 1566-1588, 2023.
arXiv Journal
Spectral gap-based deterministic tensor completion
with Kameron Decker Harris, Oscar López, and Angus Read, 14th International Conference on Sampling Theory and Applications (SampTA), 2023.
arXiv Conference proceedings
Algorithmically effective differentially private synthetic data
with Yiyun He and Roman Vershynin, Proceedings of Thirty Sixth Conference on Learning Theory (COLT), PMLR 195:3941-3968, 2023.
arXiv Conference proceedings
Overparameterized random feature regression with nearly orthogonal data
with Zhichao Wang, Proceedings of The 26th International Conference on Artificial Intelligence and Statistics (AISTATS), PMLR 206:8463-8493, 2023.
arXiv Conference proceedings
Global eigenvalue fluctuations of random biregular bipartite graphs
with Ioana Dumitriu, Random Matrices: Theory and Applications, 12(3), 2350004, 2023.
arXiv Journal
On the second eigenvalue of random bipartite biregular graphs
Journal of Theoretical Probability, 36, 1269–1303, 2023.
arXiv Journal
Sparse recovery properties of discrete random matrices
with Asaf Ferber, Ashwin Sah, and Mehtaab Sawhney, Combinatorics, Probability and Computing, 32(2), 316-325, 2023.
arXiv Journal
Deterministic tensor completion with hypergraph expanders
with Kameron Decker Harris, SIAM Journal on Mathematics of Data Science, 3(4), 1117-1140, 2021.
arXiv Journal
Spectra of random regular hypergraphs
with Ioana Dumitriu, The Electronic Journal of Combinatorics, 28(3), P3-36, 2021.
arXiv Journal
Sparse random tensors: Concentration, regularization and applications
with Zhixin Zhou, Electronic Journal of Statistics, 15(1), 2483-2516, 2021.
arXiv Journal
Community detection in the sparse hypergraph stochastic block model
with Soumik Pal, Random Structures and Algorithms, 59(3): 407– 463, 2021.
arXiv Journal
Asymptotic behavior of a sequence of conditional probability distributions and the canonical ensemble
with Yu-Chen Cheng and Hong Qian, Annales Henri Poincaré, 22, 1561–1627, 2021.
arXiv Journal
Eigenvalues of the non-backtracking operator detached from the bulk
with Simon Coste, Random Matrices: Theory and Applications, 10(3), 2150028, 2021.
arXiv Journal
Exact recovery in the hypergraph stochastic block model: A spectral algorithm
with Sam Cole, Linear Algebra and its Applications, 593, 45-73, 2020.
arXiv Journal
A graphon approach to limiting spectral distributions of Wigner-type matrices
Random Structures and Algorithms, 56(1), 251– 279, 2020.
arXiv Journal
Sparse general Wigner-type matrices: Local law and eigenvector delocalization
with Ioana Dumitriu, Journal of Mathematical Physics, 60(2), 023301, 2019.
arXiv Journal

Publications

Preprints

Spectra of high-dimensional sparse random geometric graphs*

Central limit theorems for linear spectral statistics of inhomogeneous random graphs with graphon limits*

Papers

Non-backtracking eigenvalues and eigenvectors of random regular graphs and hypergraphs*

Spectra of high-dimensional sparse random geometric graphs^*

Central limit theorems for linear spectral statistics of inhomogeneous random graphs with graphon limits^*

Non-backtracking eigenvalues and eigenvectors of random regular graphs and hypergraphs^*