Corpus ID: 11226209

Weighted Classification Cascades for Optimizing Discovery Significance in the HiggsML Challenge

@inproceedings{Mackey2014WeightedCC,
  title={Weighted Classification Cascades for Optimizing Discovery Significance in the HiggsML Challenge},
  author={L. Mackey and J. Bryan and Man Yue Mo},
  booktitle={HEPML@NIPS},
  year={2014}
}
  • L. Mackey, J. Bryan, Man Yue Mo
  • Published in HEPML@NIPS 2014
  • Mathematics, Computer Science
  • We introduce a minorization-maximization approach to optimizing common measures of discovery significance in high energy physics. The approach alternates between solving a weighted binary classification problem and updating class weights in a simple, closed-form manner. Moreover, an argument based on convex duality shows that an improvement in weighted classification error on any round yields a commensurate improvement in discovery significance. We complement our derivation with experimental… CONTINUE READING
    How machine learning won the Higgs boson challenge
    2
    Data Science as a New Frontier for Design
    3
    Consistent optimization of AMS by logistic loss minimization
    Consistent optimization of AMS by logistic loss minimization
    4
    Higgs Boson Discovery with Boosted Trees
    68

    References

    Publications referenced by this paper.
    SHOWING 1-8 OF 8 REFERENCES
    Caloric restriction improves health and survival of rhesus monkeys
    276
    A Cylinder Shear Apparatus
    18
    Overlapped Discrete Multitone Modulation for High Speed Copper Wire Communication
    288
    Asymptotic formulae for likelihood-based tests of new physics
    2232
    Quantization via Empirical Divergence Maximization
    • M. Lexa
    • Computer Science, Mathematics
    • 2012
    5
    Eilam Gross, and Ofer Vitells Asymptotic formulae for likelihoodbased tests of new physics
    • 2011
    Estimating Divergence Functionals and the Likelihood Ratio by Convex Risk Minimization
    360
    On Divergences and Informations in Statistics and Information Theory
    417