Incorporating Unlabeled Data into Distributionally Robust Learning

    Frogner Charlie
    Frogner Charlie
    Claici Sebastian
    Claici Sebastian
    Chien Edward
    Chien Edward
    Cited by: 0|Bibtex|Views18|Links

    Abstract:

    We study a robust alternative to empirical risk minimization called distributionally robust learning (DRL), in which one learns to perform against an adversary who can choose the data distribution from a specified set of distributions. We illustrate a problem with current DRL formulations, which rely on an overly broad definition of all...More

    Code:

    Data:

    Your rating :
    0

     

    Tags
    Comments