The entropy regularization information criterion

被引：0

作者：

Smola, AJ ^{[1
]}

Shawe-Taylor, J ^{[1
]}

Schölkopf, B ^{[1
]}

Williamson, RC ^{[1
]}

机构：

[1] Australian Natl Univ, Dept Engn & RSISE, Canberra, ACT 0200, Australia

来源：

ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 12 | 2000年 / 12卷

关键词：

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Effective methods of capacity control via uniform convergence bounds for function expansions have been largely limited to Support Vector machines, where good bounds are obtainable by the entropy number approach. We extend these methods to systems with expansions in terms of arbitrary (parametrized) basis functions and a wide range of regularization methods covering the whole range of general linear additive models. This is achieved by a data dependent analysis of the eigenvalues of the corresponding design matrix.

引用

页码：342 / 348

页数：7

共 50 条

[1] Optimal design of regularization term and regularization parameter by subspace information criterion
Sugiyama, M
Ogawa, H
NEURAL NETWORKS, 2002, 15 (03) : 349 - 361
[2] Regularization Parameter Selections via Generalized Information Criterion
Zhang, Yiyun
Li, Runze
Tsai, Chin-Ling
JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION, 2010, 105 (489) : 312 - 323
[3] Stochastic information gradient algorithms under (h, φ)-entropy criterion
Chen, Badong
Hu, Jinchun
Li, Hongbo
Sun, Zengqi
DYNAMICS OF CONTINUOUS DISCRETE AND IMPULSIVE SYSTEMS-SERIES B-APPLICATIONS & ALGORITHMS, 2006, 13E : 2107 - 2110
[4] Modeling biomass hydrothermal carbonization by the maximum information entropy criterion
Gallifuoco, Alberto
Papa, Alessandro Antonio
Taglieri, Luca
REACTION CHEMISTRY & ENGINEERING, 2021, 6 (05): : 920 - 928
[5] Principal component selection via adaptive regularization method and generalized information criterion
Park, Heewon
Konishi, Sadanori
STATISTICAL PAPERS, 2017, 58 (01) : 147 - 160
[6] Tomographic Inversion of Urban Area via Tikhonov Regularization and Bayesian Information Criterion
Bi, Hui
Xu, Weihao
Jin, Shuang
Zhang, Jingjing
IEEE SENSORS LETTERS, 2025, 9 (02)
[7] Principal component selection via adaptive regularization method and generalized information criterion
Heewon Park
Sadanori Konishi
Statistical Papers, 2017, 58 : 147 - 160
[8] Regularization of currents and entropy
Dinh, TC
Sibony, N
ANNALES SCIENTIFIQUES DE L ECOLE NORMALE SUPERIEURE, 2004, 37 (06): : 959 - 971
[9] Quantum entropy regularization
Silver, RN
MAXIMUM ENTROPY AND BAYESIAN METHODS, 1999, 105 : 91 - 98
[10] Bayes information criterion for Tikhonov regularization with linear constraints: Application to spectral data estimation
Carvalho, P
Santos, A
Dourado, A
Ribeiro, B
16TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION, VOL I, PROCEEDINGS, 2002, : 696 - 700

← 1 2 3 4 5 →