复杂性正则化与局部度量熵
Complexity Regularization and Local Metric Entropy
摘要:
在结构风险最小化的背景下,提出了一个序列的类$\{\mathcal{G}_j\}$,从其中,给定一个随机样本$(X_i,Y_i)$要选择一个强一致的估计。对于某些类型的函数类,我们提出了一个标准来选择一个估计,基于经验误差和复杂性惩罚$r(n,j)$在每个类$\G_j$的总和最小化。我们还提出了其他几个结果,以及在当前文献中发现的重要结果,试图提出和统一的理论在回归估计的背景下。特别地,我们在回归估计的背景下给出了结构风险最小化的一致性的推广,这些都是第5章中的新结果。
英文摘要:
In the context of Structural Risk Minimization, one is presented a sequence of classes $\{\mathcal{G}_j\}$ from which, given a random sample $(X_i,Y_i)$ one wants to choose a strongly consistent estimator. For certain types of classes of functions, we present a criterion to choose an estimator, based on the minimization of the sum of empirical error and a complexity penalty $r(n,j)$ over each class $\G_j$. We present also several other results together with important results found on current literature on the subject, in an attempt to present and unify the theory in the context of regression estimation. In particular we present a generalization of the consistency of Structural Risk Minimization in the context of regression estimation which are all new results found on Chapter 5.
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。