{
  "id": "2408.01336",
  "version": "v1",
  "published": "2024-08-02T15:33:04.000Z",
  "updated": "2024-08-02T15:33:04.000Z",
  "title": "Sparse Linear Regression when Noises and Covariates are Heavy-Tailed and Contaminated by Outliers",
  "authors": [
    "Takeyuki Sasai",
    "Hironori Fujisawa"
  ],
  "comment": "This research builds on and improves the results of arxiv:2206.07594. There will be no further update for the earlier manuscript",
  "categories": [
    "stat.ML",
    "cs.LG"
  ],
  "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.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2024-08-02T15:33:04.000Z"
    }
  ],
  "analyses": {
    "subjects": [
      "62J07"
    ],
    "keywords": [
      "sparse linear regression",
      "covariates",
      "heavy tailed distributions",
      "sharp error bounds",
      "problem estimating coefficients"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}