The convexity and design of composite multiclass losses
We consider composite loss functions for multiclass prediction comprising a proper (i.e., Fisher-consistent) loss over probability distributions and an inverse link function. We establish conditions for their (strong) convexity and explore the implications. We also show how the separation of concerns afforded by using this composite representation allows for the design of families of losses with the same Bayes risk.
|Collections||ANU Research Publications|
|Source:||Proceedings of the 29th International Conference on Machine Learning, ICML 2012|
|01_Reid_The_convexity_and_design_of_2012.pdf||741.65 kB||Adobe PDF||Request a copy|
Items in Open Research are protected by copyright, with all rights reserved, unless otherwise indicated.