Loss functions for binary classification and class probability estimation

@inproceedings{Shen2005LossFF,
  title={Loss functions for binary classification and class probability estimation},
  author={Yi Shen},
  year={2005}
}
LOSS FUNCTIONS FOR BINARY CLASSIFICATION AND CLASS PROBABILITY ESTIMATION YI SHEN SUPERVISOR: ANDREAS BUJA What are the natural loss functions for binary class probability estimation? This question has a simple answer: so-called “proper scoring rules”. These loss functions, known from subjective probability, measure the discrepancy between true probabilities and estimates thereof. They comprise all commonly used loss functions: log-loss, squared error loss, boosting loss (which we derive from… CONTINUE READING

Citations

Publications citing this paper.
SHOWING 1-10 OF 16 CITATIONS

A scaled Bregman theorem with applications

VIEW 3 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

A General Data Renewal Model for Prediction Algorithms in Industrial Data Analytics

Hongzhi Wang, Yijie Yang, Yang Song
  • ArXiv
  • 2019
VIEW 1 EXCERPT
CITES METHODS

A domain-adaptive two-stream U-Net for electron microscopy image segmentation

  • 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018)
  • 2018
VIEW 1 EXCERPT
CITES METHODS

Genetic Algorithm as Machine Learning for profiles recognition

  • 2015 7th International Joint Conference on Computational Intelligence (IJCCI)
  • 2015
VIEW 1 EXCERPT
CITES METHODS