preprints

Zhichao Wang, Denny Wu, Zhou Fan. Nonlinear spiked covariance matrices and signal propagation in deep neural networks.

Zhou Fan, Leying Guan, Yandi Shen, Yihong Wu. Gradient flows for empirical Bayes in high-dimensional linear models. (code)

Michael Celentano, Zhou Fan, Licong Lin, Song Mei. Mean-field variational inference with the TAP free energy: Geometric and statistical properties in linear models.

Zhou Fan, Yufan Li, Subhabrata Sen. TAP equations for orthogonally invariant spin glasses at high temperature.

Xinyi Zhong, Tianhao Wang, Zhou Fan. Approximate Message Passing for orthogonally invariant ensembles: Multivariate non-linearities and spectral initialization.

Zhou Fan and Yihong Wu. The replica-symmetric free energy for Ising spin glasses with orthogonally invariant couplings.

Zhou Fan, Iain M. Johnstone, and Yi Sun. Spiked covariances and principal components analysis in high-dimensional random effects models. (code)

publications

Tianhao Wang, Xinyi Zhong, Zhou Fan. Universality of Approximate Message Passing algorithms and tensor networks. Annals of Applied Probability, to appear.

Yufan Li, Zhou Fan, Subhabrata Sen, Yihong Wu. Random linear estimation with rotationally-invariant designs: Asymptotics at high temperature. IEEE Transactions on Information Theory, to appear.

Zehao Dou, Zhou Fan, Harrison Zhou. Rates of estimation for high-dimensional multi-reference alignment. Annals of Statistics, 2024.

Zhou Fan, Roy R. Lederman, Yi Sun, Tianhao Wang, Sheng Xu. Maximum likelihood for high-noise group orbit estimation and single-particle cryo-EM. Annals of Statistics, 2024.

Ran Cui, Roy A Elzur, Masahiro Kanai, Jacob C Ulirsch, Omer Weissbrod, Mark J Daly, Benjamin M Neale, Zhou Fan, Hilary K Finucane. Improving fine-mapping by modeling infinitesimal effects. Nature Genetics, 2024.

Michael Celentano, Zhou Fan, and Song Mei. Local convexity of the TAP free energy and AMP convergence for Z2-synchronization. Annals of Statistics, 2023.

Zhou Fan, Cheng Mao, Yihong Wu, Jiaming Xu. Spectral graph matching and regularized quadratic relaxations I: The Gaussian Model. Foundations of Computational Mathematics, 2023.

Zhou Fan, Cheng Mao, Yihong Wu, Jiaming Xu. Spectral graph matching and regularized quadratic relaxations II: Erdos-Renyi graphs and universality. Foundations of Computational Mathematics, 2023.

Zhou Fan, Yi Sun, Tianhao Wang, Yihong Wu. Likelihood landscape and maximum likelihood estimation for the discrete orbit recovery model. Communications on Pure and Applied Mathematics, 2023.

Xinyi Zhong, Chang Su, and Zhou Fan. Empirical Bayes PCA in high dimensions. Journal of the Royal Statistical Society: Series B, 2022. (code)

Zhou Fan and Iain M. Johnstone. Tracy-Widom at each edge of real covariance and MANOVA estimators. Annals of Applied Probability, 2022. (code)

Zhou Fan. Approximate Message Passing algorithms for rotationally invariant matrices. Annals of Statistics, 2022.

Zhou Fan, Yi Sun, and Zhichao Wang. Principal components in linear mixed models with general bulk. Annals of Statistics, 2021.

Sheng Xu, Zhou Fan. Iterative Alpha Expansion for estimating gradient-sparse signals from linear measurements. Journal of the Royal Statistical Society: Series B, 2021. (code)

Zhou Fan, Song Mei, and Andrea Montanari. TAP free energy, spin glasses, and variational inference. Annals of Probability, 2021.

Zhou Fan, Zhichao Wang. Spectra of the Conjugate Kernel and Neural Tangent Kernel for linear-width neural networks. Neural Information Processing Systems (NeurIPS), 2020, oral presentation. (code)

Sheng Xu, Zhou Fan, Sahand Negahban. Tree-projected gradient descent for estimating gradient-sparse parameters on graphs. Conference on Learning Theory (COLT), 2020.

Zhou Fan, Cheng Mao, Yihong Wu, Jiaming Xu. Spectral graph matching and regularized quadratic relaxations: Algorithm and theory. International Conference on Machine Learning (ICML), 2020.

Ganlin Song, Zhou Fan, John Lafferty. Surfing: Iterative optimization over incrementally trained deep networks. Neural Information Processing Systems (NeurIPS), 2019, spotlight presentation.

Zhou Fan and Iain M. Johnstone. Eigenvalue distributions of variance components estimators in high-dimensional random effects models. Annals of Statistics, 2019. (code)

Zhou Fan and Andrea Montanari. The spectral norm of random inner-product kernel matrices. Probability Theory and Related Fields, 2019.

Zhou Fan and Leying Guan. Approximate l0-penalized estimation of piecewise-constant signals on graphs. Annals of Statistics, 2018. (code)

Leying Guan, Zhou Fan, and Robert Tibshirani. Supervised learning via the "hubNet" procedure. Statistica Sinica, 2018.

Zhou Fan and Lester Mackey. An empirical Bayesian analysis of simultaneous changepoints in multiple data sequences. Annals of Applied Statistics, 2017. (code)

Zhou Fan and Andrea Montanari. How well do local algorithms solve semidefinite programs? Symposium on Theory of Computing (STOC), 2017.

Zhou Fan, Ron O. Dror, Thomas J. Mildorf, Stefano Piana, and David E. Shaw. Identifying localized changes in large systems: Change-point detection for biomolecular simulations. Proceedings of the National Academy of Sciences USA, 2015. (code)

Domenico Aiello, Hansheng Diao, Zhou Fan, Daniel O. King, Jessica Lin, Cesar E. Silva. Measurable time-restricted sensitivity. Nonlinearity, 2012.

thesis

Eigenvalues in multivariate random effects models. Ph.D. thesis, Stanford University, 2018.