Sparse Linear Regression when Noises and Covariates are Heavy-Tailed and Contaminated by Outliers

Takeyuki Sasai, Hironori Fujisawa
8/2/2024
stat.MLcs.LG

No confident code implementation found for this paper. 1 possible match can be shown below.

Abstract

We investigate a problem estimating coefficients of linear regression under sparsity assumption when covariates and noises are sampled from heavy tailed distributions. Additionally, we consider the situation where not only covariates and noises are sampled from heavy tailed distributions but also contaminated by outliers. Our estimators can be computed efficiently, and exhibit sharp error bounds.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. 1 weaker match is hidden by default — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Outlier-robust Estimation of a Sparse Linear Model Using Invexity

80% match2023

Sparsified-Learning for High-Dimensional Heavy-Tailed Locally Stationary Time Series, Concentration and Oracle Inequalities

80% match2025

Heavy-tailed Contamination is Easier than Adversarial Contamination

80% match2024

Feature Adaptation for Sparse Linear Regression

79% match2026

High-dimensional robust regression under heavy-tailed data: Asymptotics and Universality

78% match2023

Sparse Mean Estimation in Adversarial Settings via Incremental Learning

77% match2023

Cite this paper

@article{sasai2024sparse,
  title  = {Sparse Linear Regression when Noises and Covariates are Heavy-Tailed and Contaminated by Outliers},
  author = {Takeyuki Sasai and Hironori Fujisawa},
  year   = {2024},
  eprint = {2408.01336},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2408.01336v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2408.01336.svg)](https://codeofpaper.com/paper/2408.01336)

Discussion