A Deep Connection Between the Vapnik-Chervonenkis Entropy and the Rademacher Complexity

被引：17

作者：

Anguita, Davide ^{[1
]}

Ghio, Alessandro ^{[1
]}

Oneto, Luca ^{[1
]}

Ridella, Sandro ^{[1
]}

机构：

[1] Univ Genoa, Dept Elect Elect Telecommun Engn & Naval Architec, I-16145 Genoa, Italy

来源：

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS | 2014年 / 25卷 / 12期

关键词：

Complexity measures; Rademacher complexity; statistical learning theory; Vapnik-Chervonenkis (VC) entropy; MODEL SELECTION; INEQUALITIES; DIMENSION;

D O I：

10.1109/TNNLS.2014.2307359

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

In this paper, we derive a deep connection between the Vapnik-Chervonenkis (VC) entropy and the Rademacher complexity. For this purpose, we first refine some previously known relationships between the two notions of complexity and then derive new results, which allow computing an admissible range for the Rademacher complexity, given a value of the VC-entropy, and vice versa. The approach adopted in this paper is new and relies on the careful analysis of the combinatorial nature of the problem. The obtained results improve the state of the art on this research topic.

引用

页码：2202 / 2211

页数：10

共 50 条

[1] Some Results About the Vapnik-Chervonenkis Entropy and the Rademacher Complexity
Anguita, Davide
Ghio, Alessandro
Oneto, Luca
Ridella, Sandro
[J]. 2013 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2013,
[2] A local Vapnik-Chervonenkis complexity
Oneto, Luca
Anguita, Davide
Ridella, Sandro
[J]. NEURAL NETWORKS, 2016, 82 : 62 - 75
[3] A Comparison of Complexity Selection Approaches for Polynomials Based on: Vapnik-Chervonenkis Dimension, Rademacher Complexity and Covering Numbers
Klesk, Przemyslaw
[J]. ARTIFICIAL INTELLIGENCE AND SOFT COMPUTING, PT II, 2012, 7268 : 100 - 110
[4] Vapnik-Chervonenkis entropy of the spherical perceptron
Riegler, P
Seung, HS
[J]. PHYSICAL REVIEW E, 1997, 55 (03): : 3283 - 3287
[5] VAPNIK-CHERVONENKIS BOUNDS FOR GENERALIZATION
PARRONDO, JMR
VANDENBROECK, C
[J]. JOURNAL OF PHYSICS A-MATHEMATICAL AND GENERAL, 1993, 26 (09): : 2211 - 2223
[6] LEARNABILITY AND THE VAPNIK-CHERVONENKIS DIMENSION
BLUMER, A
EHRENFEUCHT, A
HAUSSLER, D
WARMUTH, MK
[J]. JOURNAL OF THE ACM, 1989, 36 (04) : 929 - 965
[7] The Vapnik-Chervonenkis Dimension: Information versus Complexity in Learning
Abu-Mostafa, Yaser S.
[J]. NEURAL COMPUTATION, 1989, 1 (03) : 312 - 317
[8] COMPLEXITY OF COMPUTING VAPNIK-CHERVONENKIS DIMENSION AND SOME GENERALIZED DIMENSIONS
SHINOHARA, A
[J]. THEORETICAL COMPUTER SCIENCE, 1995, 137 (01) : 129 - 144
[9] HOW TIGHT ARE THE VAPNIK-CHERVONENKIS BOUNDS
COHN, D
TESAURO, G
[J]. NEURAL COMPUTATION, 1992, 4 (02) : 249 - 269
[10] Vapnik-chervonenkis dimension of parallel arithmetic computations
Alonso, Cesar L.
Montana, Jose Luis
[J]. ALGORITHMIC LEARNING THEORY, PROCEEDINGS, 2007, 4754 : 107 - +

← 1 2 3 4 5 →