2017

Data-driven Optimal Cost Selection for Distributionally Robust Optimization

Blanchet, Jose, Kang, Yang, Zhang, Fan et al.

Understand

Recently, (Blanchet, Kang, and Murhy 2016, and Blanchet, and Kang 2017) showed that several machine learning algorithms, such as square-root Lasso, Support Vector Machines, and regularized logistic regression, among many others, can be represented exactly as distributionally robust optimization (DRO) problems.

  • The distributional uncertainty is defined as a neighborhood centered at the empirical distribution.
  • We propose a methodology which learns such neighborhood in a natural data-driven way.
  • We show rigorously that our framework encompasses adaptive regularization as a particular case.

Built on

  • The elements of statistical learning

    Friedman, J., Hastie, T., and Tibshirani, R. (2001) · 2001

    Earlier work this paper cites.

  • Distance metric learning with application to clustering with side-information

    Xing, E. P., Ng, A. Y., Jordan, M. I., and Russell, S. (2002) · 2002

    Earlier work this paper cites.

  • Learning a distance metric from relative comparisons

    Schultz, M. and Joachims, T. (2004) · 2004

    Earlier work this paper cites.

  • The adaptive lasso and its oracle properties

    Zou, H. (2006) · 2006

    Earlier work this paper cites.

  • Optimal transport: old and new

    Villani, C. (2008) · 2008

    Earlier work this paper cites.

Similar

Then

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…