资源分类
》 资源 》论文》The Local Rademacher Complexity of `p-Norm Multiple Kernel Learning

The Local Rademacher Complexity of `p-Norm Multiple Kernel Learning

2020-01-08 | |  79 |   41 |   0

Abstract

We derive an upper bound on the local Rademacher complexity of 图片.png -norm multiple kernel learning, which yields a tighter excess risk bound than global approaches. Previous local approaches analyzed the case 图片.png only while our analysis covers all cases 图片.pngassuming the different feature mappings corresponding to the different kernels to be uncorrelated. We also show a lower bound that shows that the bound is tight, and derive consequences regarding ex-cess loss, namely fast convergence rates of the order 图片.png where 图片.png is the minimum eigenvalue decay rate of the individual kernels.

上一篇：Unifying Non-Maximum Likelihood Learning Objectives with Minimum KL Contraction

下一篇：Environmental statistics and the trade-off between model-based and TD learning in humans

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...

  • A Mathematical Mo...

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

  • Rating-Boosted La...

    The performance of a recommendation system reli...