activity
20132023
most citedAnalysis of time-frequency scattering transforms

46 citations · 146 across the 18 of their papers we have counts for

collaborators

19 papers

math.NA2023

Multiscale estimates for the condition number of non-harmonic Fourier matrices

Weilin Li

This paper studies the extreme singular values of non-harmonic Fourier matrices. Such a matrix of size can be written as $Φ=[ e^{-2πi j x_k}]_{j=0,1,\dots,m-1, k=1,2,\d…

cs.IT2021

Approximation with one-bit polynomials in Bernstein form

C. Sinan Güntürk, Weilin Li

We prove various theorems on approximation using polynomials with integer coefficients in the Bernstein basis of any given order. In the extreme, we draw the coefficients from $\{…

cs.LG2021★ 5 cited

Approximation of functions with one-bit neural networks

C. Sinan Güntürk, Weilin Li

The celebrated universal approximation theorems for neural networks roughly state that any reasonable function can be arbitrarily well-approximated by a network whose parameters ar…

cs.IT2021★ 37 cited

Stability and Super-resolution of MUSIC and ESPRIT for Multi-snapshot Spectral Estimation

Weilin Li, Zengying Zhu, Weiguo Gao +1

This paper studies the spectral estimation problem of estimating the locations of a fixed number of point sources given multiple snapshots of Fourier measurements collected by a un…

cs.CV2021

Exploring the high dimensional geometry of HSI features

Wojciech Czaja, Ilya Kavalerov, Weilin Li

We explore feature space geometries induced by the 3-D Fourier scattering transform and deep neural network with extended attribute profiles on four standard hyperspectral images.…

cs.CV2021

Maximal function pooling with applications

Wojciech Czaja, Weilin Li, Yiran Li +1

Inspired by the Hardy-Littlewood maximal function, we propose a novel pooling strategy which is called maxfun pooling. It is presented both as a viable alternative to some of the m…

cs.IT2021

Quantization for spectral super-resolution

C. Sinan Güntürk, Weilin Li

We show that the method of distributed noise-shaping beta-quantization offers superior performance for the problem of spectral super-resolution with quantization whenever there is…

math.NA2020★ 1 cited

A range characterization of the single-quadrant ADRT

Weilin Li, Kui Ren, Donsub Rim

This work characterizes the range of the single-quadrant approximate discrete Radon transform (ADRT) of square images. The characterization follows from a set of linear constraints…

math.NA2020★ 1 cited

Generalization error of minimum weighted norm and kernel interpolation

Weilin Li

We study the generalization error of functions that interpolate prescribed data points and are selected by minimizing a weighted norm. Under natural and general conditions, we prov…

cs.CV2019★ 1 cited

Three-Dimensional Fourier Scattering Transform and Classification of Hyperspectral Images

Ilya Kavalerov, Weilin Li, Wojciech Czaja +1

Recent developments in machine learning and signal processing have resulted in many new techniques that are able to effectively capture the intrinsic yet complex properties of hype…

cs.IT2019★ 2 cited

Conditioning of restricted Fourier matrices and super-resolution of MUSIC

Weilin Li, Wenjing Liao

This paper studies stable recovery of a collection of point sources from its noisy low-frequency Fourier coefficients. We focus on the super-resolution regime where the minim…

cs.IT2019★ 4 cited

Super-resolution limit of the ESPRIT algorithm

Weilin Li, Wenjing Liao, Albert Fannjiang

The problem of imaging point objects can be formulated as estimation of an unknown atomic measure from its consecutive noisy Fourier coefficients. The standard resolution of…

cs.IT2019

High-performance quantization for spectral super-resolution

C. Sinan Güntürk, Weilin Li

We show that the method of distributed noise-shaping beta-quantization offers superior performance for the problem of spectral super-resolution with quantization whenever there is…

math.FA2017★ 6 cited

Rotationally invariant time-frequency scattering transforms

Wojciech Czaja, Weilin Li

In this paper we construct directionally sensitive functions that can be viewed as directional time-frequency representations. We call such a sequence a rotational uniform covering…

cs.IT2017★ 31 cited

Stable super-resolution limit and smallest singular value of restricted Fourier matrices

Weilin Li, Wenjing Liao

We consider the inverse problem of recovering the locations and amplitudes of a collection of point sources represented as a discrete measure, given of its noisy low-frequenc…

cs.IT2017★ 8 cited

Elementary error estimates for super-resolution de-noising

Weilin Li

This paper studies the problem of recovering a discrete complex measure on the torus from a finite number of corrupted Fourier samples. We assume the support of the unknown discret…

math.FA2016★ 46 cited

Analysis of time-frequency scattering transforms

Wojciech Czaja, Weilin Li

In this paper we address the problem of constructing a feature extractor which combines Mallat's scattering transform framework with time-frequency (Gabor) representations. To do t…

math.FA2016★ 4 cited

Super-resolution by means of Beurling minimal extrapolation

John J. Benedetto, Weilin Li

Let be the space of complex bounded Radon measures defined on the -dimensional torus group , equipped with the total va…

math.AP2013

Boundary Value Problems on a Half Sierpinski Gasket

Weilin Li, Robert S. Strichartz

We study boundary value problems for the Laplacian on a domain consisting of the left half of the Sierpinski Gasket (), whose boundary is essentially a countable set of poi…