arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1207.4113cs.LGstat.ML
收藏

在线核预测与复杂性逼近原理

On-line Prediction with Kernels and the Complexity Approximation Principle

Royal Holloway, University of London(伦敦大学皇家霍洛威学院)

Alex Gammerman, Yuri Kalnishkan, Vladimir Vovk

摘要:

本文描述了聚集算法在回归问题中的一个应用。它概括了早期的结果与普通的线性回归核技术,并提出了一个在线算法,执行几乎以及任何不经意的核预测。本文包含推导估计的性能,这种算法。估计,然后使用复杂性近似原理的内核方法的应用程序。

英文摘要:

The paper describes an application of Aggregating Algorithm to the problem of regression. It generalizes earlier results concerned with plain linear regression to kernel techniques and presents an on-line algorithm which performs nearly as well as any oblivious kernel predictor. The paper contains the derivation of an estimate on the performance of this algorithm. The estimate is then used to derive an application of the Complexity Approximation Principle to kernel methods.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑