Model complexity control and statistical learning theory

被引：37
|
作者：
Vladimir Cherkassky
机构：
[1] University of Minnesota,Department of Electrical and Computer Engineering
来源：
Natural Computing | 2002年 / 1卷 / 1期
关键词：
complexity control; model selection; prediction risk; predictive learning; signal denoising; statistical learning theory; VC-generalization bounds; wavelet thresholding;
D O I：
10.1023/A:1015007927558
中图分类号：
学科分类号：
摘要：
We discuss the problem of modelcomplexity control also known as modelselection. This problem frequently arises inthe context of predictive learning and adaptiveestimation of dependencies from finite data.First we review the problem of predictivelearning as it relates to model complexitycontrol. Then we discuss several issuesimportant for practical implementation ofcomplexity control, using the frameworkprovided by Statistical Learning Theory (orVapnik-Chervonenkis theory). Finally, we showpractical applications of Vapnik-Chervonenkis(VC) generalization bounds for model complexitycontrol. Empirical comparisons of differentmethods for complexity control suggestpractical advantages of using VC-based modelselection in settings where VC generalizationbounds can be rigorously applied. We also arguethat VC-theory provides methodologicalframework for complexity control even when itstechnical results can not be directly applied.
引用
收藏
页码：109 / 133
页数：24
相关论文
共 50 条
  • [1] Complexity control in statistical learning
    Jalnapurkar, SM
    [J]. SADHANA-ACADEMY PROCEEDINGS IN ENGINEERING SCIENCES, 2006, 31 (2): : 155 - 171
  • [2] Complexity control in statistical learning
    Sameer M. Jalnapurkar
    [J]. Sadhana, 2006, 31 : 155 - 171
  • [3] Statistical learning in control and matrix theory
    Vidyasagar, M
    [J]. NONLINEAR MODELING: ADVANCED BLACK-BOX TECHNIQUES, 1998, : 177 - 207
  • [4] AN AUTOMATIC MODEL IN STATISTICAL LEARNING THEORY
    FEICHTIN.G
    [J]. KYBERNETIK, 1970, 6 (06): : 237 - &
  • [5] Robust predictive control by statistical learning theory
    Stecha, J
    Vlcek, Z
    [J]. PROCEEDINGS OF THE 2001 IEEE INTERNATIONAL SYMPOSIUM ON INTELLIGENT CONTROL (ISIC'01), 2001, : 62 - 66
  • [6] Statistical learning theory and randomized algorithms for control
    Vidyasagar, M
    [J]. IEEE CONTROL SYSTEMS MAGAZINE, 1998, 18 (06): : 69 - 85
  • [7] An introduction to computational complexity and statistical learning theory applied to nuclear models
    Idini, Andrea
    [J]. 28TH INTERNATIONAL NUCLEAR PHYSICS CONFERENCE, INPC 2022, 2023, 2586
  • [8] Statistical Complexity of Quantum Learning
    Banchi, Leonardo
    Pereira, Jason Luke
    Jose, Sharu Theresa
    Simeone, Osvaldo
    [J]. ADVANCED QUANTUM TECHNOLOGIES, 2024,
  • [9] Statistical learning control of uncertain systems: theory and algorithms
    Koltchinskii, V
    Abdallah, CT
    Ariola, M
    Dorato, P
    [J]. APPLIED MATHEMATICS AND COMPUTATION, 2001, 120 (1-3) : 31 - 43
  • [10] Improved sample complexity estimates for statistical learning control of uncertain systems
    Koltchinskii, V
    Abdallah, CT
    Ariola, M
    Dorato, P
    Panchenko, D
    [J]. IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 2000, 45 (12) : 2383 - 2388
12345