Risk-Based Generalizations of f-divergences

Risk-Based Generalizations of f-divergences
复制标题

f-散度的基于风险的概括

DOI:
--
复制
发表时间:
2011
期刊:
--
影响因子:
--
通讯作者:
Raúl Santos
Raúl Santos
中科院分区:
--
文献类型:
--
作者:
Dario García;U. V. Luxburg;Raúl Santos

文献摘要

被引文献

相似文献

我们得到一个广义的f-发散的概念,称为(f,l)-发散。我们发现,这种推广享有许多良好的性能的f-发散,虽然它是一个更丰富的家庭。它还提供了替代风险方面的标准差异的替代定义。作为这个理论的第一个实际应用,我们推导出一个新的估计Kulback-Leibler分歧,我们使用的向量集聚类。
We derive a generalized notion of f-divergences, called (f, l)-divergences. We show that this generalization enjoys many of the nice properties of f-divergences, although it is a richer family. It also provides alternative definitions of standard divergences in terms of surrogate risks. As a first practical application of this theory, we derive a new estimator for the Kulback-Leibler divergence that we use for clustering sets of vectors.