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

[41] Vapnik-Chervonenkis dimension of axis-parallel cuts
Gey, Servane
[J]. COMMUNICATIONS IN STATISTICS-THEORY AND METHODS, 2018, 47 (09) : 2291 - 2296
[42] Vapnik-Chervonenkis (VC) learning theory and its applications
Cherkassky, V
Mulier, F
[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS, 1999, 10 (05): : 985 - 987
[43] Vapnik-Chervonenkis dimension of neural networks with binary weights
Mertens, S
Engel, A
[J]. PHYSICAL REVIEW E, 1997, 55 (04) : 4478 - 4488
[44] Adaptive Neural Topology Based on Vapnik-Chervonenkis Dimension
Perez-Sanchez, Beatriz
Fontenla-Romero, Oscar
Guijarro-Berdinas, Bertha
[J]. AGENTS AND ARTIFICIAL INTELLIGENCE, ICAART 2014, 2015, 8946 : 194 - 210
[45] Vapnik-Chervonenkis generalization bounds for real valued neural networks
Hole, A
[J]. NEURAL COMPUTATION, 1996, 8 (06) : 1277 - 1299
[46] General Vapnik-Chervonenkis dimension bounds for quantum circuit learning
Chen, Chih-Chieh
Sogabe, Masaru
Shiba, Kodai
Sakamoto, Katsuyoshi
Sogabe, Tomah
[J]. JOURNAL OF PHYSICS-COMPLEXITY, 2022, 3 (04):
[47] INAPPROXIMABILITY OF TRUTHFUL MECHANISMS VIA GENERALIZATIONS OF THE VAPNIK-CHERVONENKIS DIMENSION
Daniely, Amit
Schapira, Michael
Shahaf, Gal
[J]. SIAM JOURNAL ON COMPUTING, 2018, 47 (01) : 96 - 120
[48] Lower bounds on the vapnik-chervonenkis dimension of convex polytope classifiers
Takacs, Gabor
Pataki, Bela
[J]. INES 2007: 11TH INTERNATIONAL CONFERENCE ON INTELLIGENT ENGINEERING SYSTEMS, PROCEEDINGS, 2007, : 145 - +
[49] UNIFORM CONVERGENCE OF VAPNIK-CHERVONENKIS CLASSES UNDER ERGODIC SAMPLING
Adams, Terrence M.
Nobel, Andrew B.
[J]. ANNALS OF PROBABILITY, 2010, 38 (04): : 1345 - 1367
[50] Vapnik-Chervonenkis type conditions and uniform Donsker classes of functions
Talagrand, M
[J]. ANNALS OF PROBABILITY, 2003, 31 (03): : 1565 - 1582

← 1 2 3 4 5 →