资源分类
》 资源 》论文》The Convexity and Design of Composite Multiclass Losses

The Convexity and Design of Composite Multiclass Losses

2020-02-28 | |  54 |   42 |   0

Abstract

We consider composite loss functions for multiclass prediction comprising a proper (i.e., Fisherconsistent) 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.

上一篇：Lognormal and Gamma Mixed Negative Binomial Regression

下一篇：Learning with Augmented Features for Heterogeneous Domain Adaptation

用户评价
全部评价

热门资源

  • Learning to Predi...

    Much of model-based reinforcement learning invo...

  • Stratified Strate...

    In this paper we introduce Stratified Strategy ...

  • The Variational S...

    Unlike traditional images which do not offer in...

  • Learning to learn...

    The move from hand-designed features to learned...

  • A Mathematical Mo...

    Direct democracy, where each voter casts one vo...