Add to ORKGVidyasagar M, Balaji S, Hammer B. Closure properties of uniform convergence of empirical means and PAC learnability under a family of probability measures. System and Control Letters. 2001;42:151-157
A large number of results are available about the weak convergence of probability measures in spaces...
In this thesis we define two most common types of convergence of probability measures and show relat...
We narrow the width of the confidence interval introduced by Vapnik and Chervonenkis for the risk fu...
Learnability in Valiant's PAC learning model has been shown to be strongly related to the exist...
证明了如果函数族F具有UCEM性质,那么F是完全有界的.此外如果F关于概率族P是PAC可学习的或具有UCEM性质,则F关于P的闭包也具有同样的性质.构造了一个非多项式可学习的例子,说明了PAC可学习的...
Thesis (Ph.D.)--Massachusetts Institute of Technology, Dept. of Mathematics, 1982.MICROFICHE COPY AV...
We consider some problems in learning with respect to a fixed distribution. We introduce two new not...
It is proved that the UCEM property of a family of measurable functions F implies that F is totally ...
Abstract. The hypo-convergence of upper semicontinuous functions provides a natural framework for th...
This book provides a thorough exposition of the main concepts and results related to various types o...
It has been shown previously by Nobel and Dembo (Stat. Probab. Lett. 17 (1993) 169) that, if a famil...
International audienceThe study of finite approximations of probability measures has a long history....
In this paper, uniformly consistent estimation (learnability) of decision rules for pattern classifi...
In this paper, a brief introduction is given to some statistical aspects of PAC (probably approximat...
The uniform empirical integral differences of Sethuraman\u27s large deviation theorem are proved to ...
A large number of results are available about the weak convergence of probability measures in spaces...
In this thesis we define two most common types of convergence of probability measures and show relat...
We narrow the width of the confidence interval introduced by Vapnik and Chervonenkis for the risk fu...
Learnability in Valiant's PAC learning model has been shown to be strongly related to the exist...
证明了如果函数族F具有UCEM性质,那么F是完全有界的.此外如果F关于概率族P是PAC可学习的或具有UCEM性质,则F关于P的闭包也具有同样的性质.构造了一个非多项式可学习的例子,说明了PAC可学习的...
Thesis (Ph.D.)--Massachusetts Institute of Technology, Dept. of Mathematics, 1982.MICROFICHE COPY AV...
We consider some problems in learning with respect to a fixed distribution. We introduce two new not...
It is proved that the UCEM property of a family of measurable functions F implies that F is totally ...
Abstract. The hypo-convergence of upper semicontinuous functions provides a natural framework for th...
This book provides a thorough exposition of the main concepts and results related to various types o...
It has been shown previously by Nobel and Dembo (Stat. Probab. Lett. 17 (1993) 169) that, if a famil...
International audienceThe study of finite approximations of probability measures has a long history....
In this paper, uniformly consistent estimation (learnability) of decision rules for pattern classifi...
In this paper, a brief introduction is given to some statistical aspects of PAC (probably approximat...
The uniform empirical integral differences of Sethuraman\u27s large deviation theorem are proved to ...
A large number of results are available about the weak convergence of probability measures in spaces...
In this thesis we define two most common types of convergence of probability measures and show relat...
We narrow the width of the confidence interval introduced by Vapnik and Chervonenkis for the risk fu...