Corpus ID: 227054176

List-Decodable Mean Estimation in Nearly-PCA Time

  title={List-Decodable Mean Estimation in Nearly-PCA Time},
  author={Ilias Diakonikolas and D. Kane and Daniel Kongsgaard and J. Li and Kevin Tian},
  • Ilias Diakonikolas, D. Kane, +2 authors Kevin Tian
  • Published 2020
  • Computer Science, Mathematics
  • ArXiv
  • Traditionally, robust statistics has focused on designing estimators tolerant to a minority of contaminated data. Robust list-decodable learning focuses on the more challenging regime where only a minority $\frac 1 k$ fraction of the dataset is drawn from the distribution of interest, and no assumptions are made on the remaining data. We study the fundamental task of list-decodable mean estimation in high dimensions. Our main result is a new list-decodable mean estimation algorithm for bounded… CONTINUE READING


    List-Decodable Mean Estimation via Iterative Multi-Filtering
    • 3
    • PDF
    List Decodable Learning via Sum of Squares
    • 29
    • PDF
    High-Dimensional Robust Mean Estimation in Nearly-Linear Time
    • 61
    • PDF
    How Hard Is Robust Mean Estimation?
    • 17
    • PDF
    List-Decodable Subspace Recovery via Sum-of-Squares
    • 14
    Robust Estimators in High Dimensions without the Computational Intractability
    • 199
    • PDF
    List-Decodable Linear Regression
    • 30
    • PDF