arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2006.09223stat.MLcs.LGmath.STstat.TH
收藏

普通线性回归学习无穷多个响应函数的风险界

Risk bounds when learning infinitely many response functions by ordinary linear regression

École Polytechnique(巴黎综合理工学院);Institut Polytechnique de Paris(巴黎理工学院);Lagrange Mathematics and Computing Research Center(拉格朗日数学与计算研究中心);Télécom Paris(巴黎电信学院);CREST(国家科学研究中心);ENSAI(法国国家统计与信息分析学院);UCLouvain(鲁汶大学)

Vincent Plassier, François Portier, Johan Segers

摘要:

考虑基于相同输入变量同时学习大量响应函数的问题。训练数据由从公共分布中抽取的输入变量的单个独立随机样本以及相关响应组成。输入变量被映射到一个高维线性空间,称为特征空间,响应函数被建模为映射特征的线性泛函,系数通过普通最小二乘法校准。我们提供收敛保证的最坏情况下的超额预测风险,通过控制的过度风险的收敛速度一致的响应函数。允许特征图的维度随着样本量而趋于无穷大。响应函数的集合虽然可能是无限的,但应该具有有限的Vapnik-Chervonenkis维数。当在合理的计算时间内建立多个代理模型时,可以应用导出的边界。

英文摘要:

Consider the problem of learning a large number of response functions simultaneously based on the same input variables. The training data consist of a single independent random sample of the input variables drawn from a common distribution together with the associated responses. The input variables are mapped into a high-dimensional linear space, called the feature space, and the response functions are modelled as linear functionals of the mapped features, with coefficients calibrated via ordinary least squares. We provide convergence guarantees on the worst-case excess prediction risk by controlling the convergence rate of the excess risk uniformly in the response function. The dimension of the feature map is allowed to tend to infinity with the sample size. The collection of response functions, although potentially infinite, is supposed to have a finite Vapnik-Chervonenkis dimension. The bound derived can be applied when building multiple surrogate models in a reasonable computing time.

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。

↑