Partitioned Cross-validation
نویسنده
چکیده
Partitioned cross-validation is proposed as a method for overcoming the large amounts of across sample variability to which ordinary cross-validation is subject. The price for cutting down on the sample noise is that a type of bias is introduced. A theory is presented for optimal trade-off of this variance and bias. Comparison with other bandwidth selection methods is given.
منابع مشابه
Comparison of Two Bandwidth Selectors with Dependent Errors
For nonparametric regression. in the case of dependent observations. cross-validation is known to be severely affected by dependence. This effect is precisely quantified through a limiting distribution for the cross-validated bandwidth. The performance of two methods. the "leave-(2e+1)-out" version of cross-validation and partitioned cross-validation. which adjust for the dependence effect on b...
متن کاملTowards Privacy-Preserving Model Selection
Model selection is an important problem in statistics, machine learning, and data mining. In this paper, we investigate the problem of enabling multiple parties to perform model selection on their distributed data in a privacy-preserving fashion without revealing their data to each other. We specifically study cross validation, a standard method of model selection, in the setting in which two p...
متن کاملControl Charts and Neural Networks for Oestrus Dectection in Dairy Cows
Exponentially weighted moving average control charts and neural networks were used for oestrus detection in dairy cows. The analysis involved 373 cows, each with one verified oestrus event. Model inputs were the traits activity, measured by pedometer, and the period (days) since last oestrus. In total 10,386 records were available, which were partitioned into training and validation subsets to ...
متن کاملComparison of Data - Driven Bandwidth Selectors
This paper provides a comparison. on three levels. of several promising data-driven methods for selecting the bandwidth of a kernel density estimator. The methods compared are: least squares cross-validation. biased cross-val idation. partitioned cross-val idation. and a plug-in rule. The levels of comparison are: asymptotic rate of convergence to the optimum, explici t calculation in the case ...
متن کاملOn Optimal Generalizability in Parametric Learning
We consider the parametric learning problem, where the objective of the learner is determined by a parametric loss function. Employing empirical risk minimization with possibly regularization, the inferred parameter vector will be biased toward the training samples. Such bias is measured by the cross validation procedure in practice where the data set is partitioned into a training set used for...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 1987