Quantizing Heavy-tailed Data in Statistical Estimation: (Near) Minimax Rates, Covariate Quantization, and Uniform Recovery

12/30/2022
by   Junren Chen, et al.
0

This paper studies the quantization of heavy-tailed data in some fundamental statistical estimation problems, where the underlying distributions have bounded moments of some order. We propose to truncate and properly dither the data prior to a uniform quantization. Our major standpoint is that (near) minimax rates of estimation error are achievable merely from the quantized data produced by the proposed scheme. In particular, concrete results are worked out for covariance estimation, compressed sensing, and matrix completion, all agreeing that the quantization only slightly worsens the multiplicative factor. Besides, we study compressed sensing where both covariate (i.e., sensing vector) and response are quantized. Under covariate quantization, although our recovery program is non-convex because the covariance matrix estimator lacks positive semi-definiteness, all local minimizers are proved to enjoy near optimal error bound. Moreover, by the concentration inequality of product process and covering argument, we establish near minimax uniform recovery guarantee for quantized compressed sensing with heavy-tailed noise.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/23/2018

Robust one-bit compressed sensing with non-Gaussian measurements

We study memoryless one-bit compressed sensing with non-Gaussian measure...
research
02/26/2022

High Dimensional Statistical Estimation under One-bit Quantization

Compared with data with high precision, one-bit (binary) data are prefer...
research
06/16/2020

Robust compressed sensing of generative models

The goal of compressed sensing is to estimate a high dimensional vector ...
research
11/18/2019

Quantized Compressed Sensing by Rectified Linear Units

This work is concerned with the problem of recovering high-dimensional s...
research
09/10/2018

Optimal variable selection and adaptive noisy Compressed Sensing

For high-dimensional linear regression model, we propose an algorithm of...
research
09/19/2020

A Unified Approach to Uniform Signal Recovery From Non-Linear Observations

Recent advances in quantized compressed sensing and high-dimensional est...
research
08/23/2021

On the Acceleration of Deep Neural Network Inference using Quantized Compressed Sensing

Accelerating deep neural network (DNN) inference on resource-limited dev...

Please sign up or login with your details

Forgot password? Click here to reset