IMPROVED UPPER-BOUNDS FOR PROBABILITIES OF UNIFORM DEVIATIONS

被引：7

作者：

LUGOSI, G ^{[1
]}

机构：

[1] TECH UNIV BUDAPEST,FAC ELECT ENGN,DEPT MATH & COMP SCI,BUDAPEST,HUNGARY

来源：

STATISTICS & PROBABILITY LETTERS | 1995年 / 25卷 / 01期

关键词：

UNIFORM DEVIATIONS; VAPNIK-CHERVONENKIS INEQUALITY; EMPIRICAL PROCESSES; CONCEPT LEARNING;

D O I：

10.1016/0167-7152(94)00207-O

中图分类号：

O21 [概率论与数理统计]; C8 [统计学];

学科分类号：

020208 ; 070103 ; 0714 ;

摘要：

We obtain Vapnik-Chervonenkis type upper bounds for the uniform deviation of probabilities from their expectations. The bounds sharpen previously known probability inequalities.

引用

页码：71 / 77

页数：7

共 12 条

[1]

ALEXANDER K, 1984, ANN PROBAB, V4, P1041

[2]

Bernstein S., 1946, THEORY PROBABILITIES

[3] LEARNABILITY AND THE VAPNIK-CHERVONENKIS DIMENSION [J].

BLUMER, A ;

EHRENFEUCHT, A ;

HAUSSLER, D ;

WARMUTH, MK .

JOURNAL OF THE ACM, 1989, 36 (04) :929-965

[4] BOUNDS FOR THE UNIFORM DEVIATION OF EMPIRICAL MEASURES [J].

DEVROYE, L .

JOURNAL OF MULTIVARIATE ANALYSIS, 1982, 12 (01) :72-79

[5]

DEVROYE L, 1976, 183 U TEX EL RES CTR

[6] CENTRAL LIMIT-THEOREMS FOR EMPIRICAL MEASURES [J].

DUDLEY, RM .

ANNALS OF PROBABILITY, 1978, 6 (06) :899-929

[7]

HAUSSLER D, 1991, IN PRESS J COMBIN TH

[8] PROBABILITY-INEQUALITIES FOR SUMS OF BOUNDED RANDOM-VARIABLES [J].

HOEFFDING, W .

JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION, 1963, 58 (301) :13-+

[9]

Sauer N., 1972, J COMB THEORY A, V13, P145, DOI [10.1016/0097-3165(72)90019-2, DOI 10.1016/0097-3165(72)90019-2]

[10] SHARPER BOUNDS FOR GAUSSIAN AND EMPIRICAL PROCESSES [J].

TALAGRAND, M .

ANNALS OF PROBABILITY, 1994, 22 (01) :28-76

← 1 2 →