A Note on Improved Loss Bounds for Multiple Kernel Learning
CoRR（2011）
摘要
In this paper, we correct an upper bound, presented in , on the
generalisation error of classifiers learned through multiple kernel learning.
The bound in uses Rademacher complexity and has anadditive
dependence on the logarithm of the number of kernels and the margin achieved by
the classifier. However, there are some errors in parts of the proof which are
corrected in this paper. Unfortunately, the final result turns out to be a risk
bound which has a multiplicative dependence on the logarithm of the
number of kernels and the margin achieved by the classifier.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树，研究论文发展脉络
Chat Paper
正在生成论文摘要