29 citations · 67 across the 6 of their papers we have counts for
4 papers · 1 filter
II. High Dimensional Estimation under Weak Moment Assumptions: Structured Recovery and Matrix Estimation
Xiaohan Wei
The purpose of this thesis is to develop new theories on high-dimensional structured signal recovery under a rather weak assumption on the measurements that only a finite number of…
Robust One-Bit Recovery via ReLU Generative Networks: Near-Optimal Statistical Rate and Global Landscape Analysis
Shuang Qiu, Xiaohan Wei, Zhuoran Yang
We study the robust one-bit compressed sensing problem whose goal is to design an algorithm that faithfully recovers any sparse target vector \textit{uniformly…
Structured Recovery with Heavy-tailed Measurements: A Thresholding Procedure and Optimal Rates
Xiaohan Wei
This paper introduces a general regularized thresholded least-square procedure estimating a structured signal from the following observations: $y_i = f(\langle…
Estimation of the covariance structure of heavy-tailed distributions
Stanislav Minsker, Xiaohan Wei
We propose and analyze a new estimator of the covariance matrix that admits strong theoretical guarantees under weak assumptions on the underlying distribution, such as existence o…