Corpus ID: 730092

Learning subgaussian classes : Upper and minimax bounds

@article{Lecu2013LearningSC,
  title={Learning subgaussian classes : Upper and minimax bounds},
  author={Guillaume Lecu{\'e} and Shahar Mendelson},
  journal={arXiv: Statistics Theory},
  year={2013}
}
  • Guillaume Lecué, Shahar Mendelson
  • Published 2013
  • Mathematics
  • arXiv: Statistics Theory
  • We obtain sharp oracle inequalities for the empirical risk minimization procedure in the regression model under the assumption that the target Y and the model F are subgaussian. The bound we obtain is sharp in the minimax sense if F is convex. Moreover, under mild assumptions on F, the error rate of ERM remains optimal even if the procedure is allowed to perform with constant probability. A part of our analysis is a new proof of minimax results for the gaussian regression model. 

    Figures from this paper.

    Citations

    Publications citing this paper.
    SHOWING 1-10 OF 53 CITATIONS

    FILTER CITATIONS BY YEAR

    2012
    2020

    CITATION STATISTICS

    • 9 Highly Influenced Citations

    • Averaged 5 Citations per year from 2018 through 2020