Corpus ID: 227306086

Non-monotone risk functions for learning

@article{Holland2020NonmonotoneRF,
  title={Non-monotone risk functions for learning},
  author={Matthew J. Holland},
  journal={ArXiv},
  year={2020},
  volume={abs/2012.02424}
}
  • Matthew J. Holland
  • Published 2020
  • Mathematics, Computer Science
  • ArXiv
  • In this paper we consider generalized classes of potentially non-monotone risk functions for use as evaluation metrics in learning tasks. The resulting risks are in general non-convex and non-smooth, which makes both the computational and inferential sides of the learning problem difficult. For random losses belonging to any Banach space, we obtain sufficient conditions for the risk functions to be weakly convex, and to admit unbiased stochastic directional derivatives. We then use recent work… CONTINUE READING

    References

    SHOWING 1-10 OF 31 REFERENCES
    Stochastic model-based minimization of weakly convex functions
    • 116
    • Highly Influential
    • PDF
    Quantitative stability in stochastic programming
    • A. Shapiro
    • Mathematics, Computer Science
    • Math. Program.
    • 1994
    • 62
    • Highly Influential
    • PDF
    Convex Analysis and Monotone Operator Theory in Hilbert Spaces
    • 2,816
    • PDF
    Integrals which are convex functionals. II
    • 471
    • PDF
    Efficiency of minimizing compositions of convex functions and smooth maps
    • 90
    • Highly Influential
    • PDF
    Generalized deviations in risk analysis
    • 140
    • PDF
    Regularization in Banach Spaces with Respect to the Bregman Distance
    • 1
    Optimization of Risk Measures
    • 116
    • PDF