Abstract
Empirical risk minimization with convex loss was studied in detail by Blanchard 324 et al. [26] and Bartlett et al. [16]. In the last paper, rather subtle bounds relating 325 excess risks with respect to a “surrogate” convex loss and with respect to the binary 326 classification loss were also studied. Earlier, Zhang [154] provided initial versions 327 of such bounds.
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Koltchinskii, V. (2011). Examples of Excess Risk Bounds in Prediction Problems. In: Oracle Inequalities in Empirical Risk Minimization and Sparse Recovery Problems. Lecture Notes in Mathematics(), vol 2033. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-22147-7_5
Download citation
DOI: https://doi.org/10.1007/978-3-642-22147-7_5
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-22146-0
Online ISBN: 978-3-642-22147-7
eBook Packages: Mathematics and StatisticsMathematics and Statistics (R0)