21 citations · 129 across the 26 of their papers we have counts for
26 papers
Random linear estimation with rotationally-invariant designs: Asymptotics at high temperature
Yufan Li, Zhou Fan, Subhabrata Sen +1
We study estimation in the linear model , in a Bayesian setting where has an entrywise i.i.d. prior and the design is rotationally-invariant in law. In…
HyperBO+: Pre-training a universal prior for Bayesian optimization with hierarchical Gaussian processes
Zhou Fan, Xinran Han, Zi Wang
Bayesian optimization (BO), while proved highly effective for many black-box function optimization tasks, requires practitioners to carefully select priors that well model their fu…
Rates of estimation for high-dimensional multi-reference alignment
Zehao Dou, Zhou Fan, Harrison Zhou
We study the continuous multi-reference alignment model of estimating a periodic function on the circle from noisy and circularly-rotated observations. Motivated by analogous high-…
TAP equations for orthogonally invariant spin glasses at high temperature
Zhou Fan, Yufan Li, Subhabrata Sen
We study the high-temperature regime of a mean-field spin glass model whose couplings matrix is orthogonally invariant in law. The magnetization of this model is conjectured to sat…
Maximum likelihood for high-noise group orbit estimation and single-particle cryo-EM
Zhou Fan, Roy R. Lederman, Yi Sun +2
Motivated by applications to single-particle cryo-electron microscopy (cryo-EM), we study several problems of function estimation in a high noise regime, where samples are observed…
Local convexity of the TAP free energy and AMP convergence for Z2-synchronization
Michael Celentano, Zhou Fan, Song Mei
We study mean-field variational Bayesian inference using the TAP approach, for Z2-synchronization as a prototypical example of a high-dimensional Bayesian model. We show that for a…
The replica-symmetric free energy for Ising spin glasses with orthogonally invariant couplings
Zhou Fan, Yihong Wu
We study a variant of the Sherrington-Kirkpatrick (S-K) spin glass model with external field, where the random symmetric couplings matrix does not consist of i.i.d. entries but is…
Empirical Bayes PCA in high dimensions
Xinyi Zhong, Chang Su, Zhou Fan
When the dimension of data is comparable to or larger than the number of data samples, Principal Components Analysis (PCA) may exhibit problematic high-dimensional noise. In this w…
Approximate Message Passing algorithms for rotationally invariant matrices
Zhou Fan
Approximate Message Passing (AMP) algorithms have seen widespread use across a variety of applications. However, the precise forms for their Onsager corrections and state evolution…
Tree-Projected Gradient Descent for Estimating Gradient-Sparse Parameters on Graphs
Sheng Xu, Zhou Fan, Sahand Negahban
We study estimation of a gradient-sparse parameter vector , having strong gradient-sparsity on an underlying g…
Spectra of the Conjugate Kernel and Neural Tangent Kernel for linear-width neural networks
Zhou Fan, Zhichao Wang
We study the eigenvalue distributions of the Conjugate Kernel and Neural Tangent Kernel associated to multi-layer feedforward neural networks. In an asymptotic regime where network…
Likelihood landscape and maximum likelihood estimation for the discrete orbit recovery model
Zhou Fan, Yi Sun, Tianhao Wang +1
We study the non-convex optimization landscape for maximum likelihood estimation in the discrete orbit recovery model with Gaussian noise. This model is motivated by applications i…
Spectral Graph Matching and Regularized Quadratic Relaxations II: Erdős-Rényi Graphs and Universality
Zhou Fan, Cheng Mao, Yihong Wu +1
We analyze a new spectral graph matching algorithm, GRAph Matching by Pairwise eigen-Alignments (GRAMPA), for recovering the latent vertex correspondence between two unlabeled, edg…
Spectral Graph Matching and Regularized Quadratic Relaxations I: The Gaussian Model
Zhou Fan, Cheng Mao, Yihong Wu +1
Graph matching aims at finding the vertex correspondence between two unlabeled graphs that maximizes the total edge weight correlation. This amounts to solving a computationally in…
Surfing: Iterative optimization over incrementally trained deep networks
Ganlin Song, Zhou Fan, John Lafferty
We investigate a sequential optimization procedure to minimize the empirical risk functional for certain families of deep network…
Iterative Alpha Expansion for estimating gradient-sparse signals from linear measurements
Sheng Xu, Zhou Fan
We consider estimating a piecewise-constant image, or a gradient-sparse signal on a general graph, from noisy linear measurements. We propose and study an iterative algorithm to mi…
Principal components in linear mixed models with general bulk
Zhou Fan, Yi Sun, Zhichao Wang
We study the principal components of covariance estimators in multivariate mixed-effects linear models. We show that, in high dimensions, the principal eigenvalues and eigenvectors…
TAP free energy, spin glasses, and variational inference
Zhou Fan, Song Mei, Andrea Montanari
We consider the Sherrington-Kirkpatrick model of spin glasses with ferromagnetically biased couplings. For a specific choice of the couplings mean, the resulting Gibbs measure is e…
Spiked covariances and principal components analysis in high-dimensional random effects models
Zhou Fan, Iain M. Johnstone, Yi Sun
We study principal components analyses in multivariate random and mixed effects linear models, assuming a spherical-plus-spikes structure for the covariance matrix of each random e…
Tracy-Widom at each edge of real covariance and MANOVA estimators
Zhou Fan, Iain M. Johnstone
We study the sample covariance matrix for real-valued data with general population covariance, as well as MANOVA-type covariance estimators in variance components models under null…
Approximate -penalized estimation of piecewise-constant signals on graphs
Zhou Fan, Leying Guan
We study recovery of piecewise-constant signals on graphs by the estimator minimizing an -edge-penalized objective. Although exact minimization of this objective may be comput…
How Well Do Local Algorithms Solve Semidefinite Programs?
Zhou Fan, Andrea Montanari
Several probabilistic models from high-dimensional statistics and machine learning reveal an intriguing --and yet poorly understood-- dichotomy. Either simple local algorithms succ…
Regularization for supervised learning via the "hubNet" procedure
Leying Guan, Zhou Fan, Robert Tibshirani
We propose a new method for supervised learning. The hubNet procedure fits a hub-based graphical model to the predictors, to estimate the amount of "connection" that each predictor…
Empirical Bayesian analysis of simultaneous changepoints in multiple data sequences
Zhou Fan, Lester Mackey
Copy number variations in cancer cells and volatility fluctuations in stock prices are commonly manifested as changepoints occurring at the same positions across related data seque…