A Modern Take on the Bias-Variance Tradeoff in Neural Networks

    Brady Neal
    Brady Neal
    Sarthak Mittal
    Sarthak Mittal
    Vinayak Tantia
    Vinayak Tantia
    Matthew Scicluna
    Matthew Scicluna

    arXiv: Learning, Volume abs/1810.08591, 2018.

    Cited by: 1|Bibtex|Views30|Links
    EI

    Abstract:

    We revisit the bias-variance tradeoff for neural networks in light of modern empirical findings. The traditional bias-variance tradeoff in machine learning suggests that as model complexity grows, variance increases. Classical bounds in statistical learning theory point to the number of parameters in a model as a measure of model complexi...More

    Code:

    Data:

    Your rating :
    0

     

    Tags
    Comments