10 citations · 29 across the 13 of their papers we have counts for
13 papers
Approximate Message Passing with Random Initialization for Phase Retrieval
Yuchen Chen, Yandi Shen, Xingyu Xu
We analyze approximate message passing (AMP) with an independent Gaussian initialization for noiseless phase retrieval in the proportional asymptotic regime. A random initializatio…
The Power of Preconditioning in Overparameterized Low-Rank Matrix Sensing
Xingyu Xu, Yandi Shen, Yuejie Chi +1
We propose $\textsf{ScaledGD($λ$)}$, a preconditioned gradient descent method to tackle the low-rank matrix sensing problem when the true rank is unknown, and when the matrix is po…
Empirical Bayes estimation: When does -modeling beat -modeling in theory (and in practice)?
Yandi Shen, Yihong Wu
Empirical Bayes (EB) is a popular framework for large-scale inference that aims to find data-driven estimators to compete with the Bayesian oracle that knows the true prior. Two pr…
Universality of regularized regression estimators in high dimensions
Qiyang Han, Yandi Shen
The Convex Gaussian Min-Max Theorem (CGMT) has emerged as a prominent theoretical tool for analyzing the precise stochastic behavior of various statistical estimators in the so-cal…
Nonparametric mixture MLEs under Gaussian-smoothed optimal transport distance
Fang Han, Zhen Miao, Yandi Shen
The Gaussian-smoothed optimal transport (GOT) framework, pioneered in Goldfeld et al. (2020) and followed up by a series of subsequent papers, has quickly caught attention among re…
Uncertainty quantification in the Bradley-Terry-Luce model
Chao Gao, Yandi Shen, Anderson Y. Zhang
The Bradley-Terry-Luce (BTL) model is a benchmark model for pairwise comparisons between individuals. Despite recent progress on the first-order asymptotics of several popular proc…
Generalized kernel distance covariance in high dimensions: non-null CLTs and power universality
Qiyang Han, Yandi Shen
Distance covariance is a popular dependence measure for two random vectors and of possibly different dimensions and types. Recent years have witnessed concentrated efforts…
Contiguity under high dimensional Gaussianity with applications to covariance testing
Qiyang Han, Tiefeng Jiang, Yandi Shen
Le Cam's third/contiguity lemma is a fundamental probabilistic tool to compute the limiting distribution of a given statistic under a non-null sequence of probability measure…
High dimensional asymptotics of likelihood ratio tests in the Gaussian sequence model under convex constraints
Qiyang Han, Bodhisattva Sen, Yandi Shen
In the Gaussian sequence model , we study the likelihood ratio test (LRT) for testing versus , where , and is a closed convex set in…
On a phase transition in general order spline regression
Yandi Shen, Qiyang Han, Fang Han
In the Gaussian sequence model in , we study the fundamental limit of approximating the signal by a class of (generalized) s…
Exponential inequalities for dependent V-statistics via random Fourier features
Yandi Shen, Fang Han, Daniela Witten
We establish exponential inequalities for a class of V-statistics under strong mixing conditions. Our theory is developed via a novel kernel expansion based on random Fourier featu…
Tail behavior of dependent V-statistics and its applications
Yandi Shen, Fang Han, Daniela Witten
We establish exponential inequalities and Cramer-type moderate deviation theorems for a class of V-statistics under strong mixing conditions. Our theory is developed via kernel exp…
Optimal estimation of variance in nonparametric regression with random design
Yandi Shen, Chao Gao, Daniela Witten +1
Consider the heteroscedastic nonparametric regression model with random design \begin{align*} Y_i = f(X_i) + V^{1/2}(X_i)\varepsilon_i, \quad i=1,2,\ldots,n, \end{align*} with $f(\…