Towards robust model selection using estimation and approximation error bounds

Joel Ratsaby; Ronny Meir; Vitaly Maiorov

doi:10.1145/238061.238069

Towards robust model selection using estimation and approximation error bounds

Joel Ratsaby
, Ronny Meir
, Vitaly Maiorov

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

6 Scopus citations

Abstract

One of the main problems in machine learning and statistical inference is selecting an appropriate model by which a set of data can be explained. A novel model selection criterion based on the uniform convergence of empirical processes combined with the results concerning the approximation ability of non-linear manifolds of functions is introduced. A coherent and robust framework for model selection was elucidated and a lower bound on the approximation error was established, giving a well specified sense for most functions of interest.

Original language	English
Title of host publication	Proceedings of the Annual ACM Conference on Computational Learning TheoryPages 57 - 671996 Proceedings of the 1996 9th Annual Conference on Computational Learning Theory28 June 1996through 1 July 1996
Pages	57-67
Number of pages	11
ISBN (Electronic)	9780897918114
DOIs	https://doi.org/10.1145/238061.238069
State	Published - 1996
Externally published	Yes
Event	Proceedings of the 1996 9th Annual Conference on Computational Learning Theory - Desenzano del Garda, Italy Duration: 28 Jun 1996 → 1 Jul 1996

Publication series

Name	Proceedings of the Annual ACM Conference on Computational Learning Theory

Conference

Conference	Proceedings of the 1996 9th Annual Conference on Computational Learning Theory
City	Desenzano del Garda, Italy
Period	28/06/96 → 1/07/96

Access to Document

10.1145/238061.238069

Cite this

Ratsaby, J., Meir, R., & Maiorov, V. (1996). Towards robust model selection using estimation and approximation error bounds. In Proceedings of the Annual ACM Conference on Computational Learning TheoryPages 57 - 671996 Proceedings of the 1996 9th Annual Conference on Computational Learning Theory28 June 1996through 1 July 1996 (pp. 57-67). (Proceedings of the Annual ACM Conference on Computational Learning Theory). https://doi.org/10.1145/238061.238069

Ratsaby, Joel ; Meir, Ronny ; Maiorov, Vitaly. / Towards robust model selection using estimation and approximation error bounds. Proceedings of the Annual ACM Conference on Computational Learning TheoryPages 57 - 671996 Proceedings of the 1996 9th Annual Conference on Computational Learning Theory28 June 1996through 1 July 1996. 1996. pp. 57-67 (Proceedings of the Annual ACM Conference on Computational Learning Theory).

@inproceedings{517d58f410c448c8825872e7ae6a3070,

title = "Towards robust model selection using estimation and approximation error bounds",

abstract = "One of the main problems in machine learning and statistical inference is selecting an appropriate model by which a set of data can be explained. A novel model selection criterion based on the uniform convergence of empirical processes combined with the results concerning the approximation ability of non-linear manifolds of functions is introduced. A coherent and robust framework for model selection was elucidated and a lower bound on the approximation error was established, giving a well specified sense for most functions of interest.",

author = "Joel Ratsaby and Ronny Meir and Vitaly Maiorov",

year = "1996",

doi = "10.1145/238061.238069",

language = "אנגלית",

series = "Proceedings of the Annual ACM Conference on Computational Learning Theory",

pages = "57--67",

booktitle = "Proceedings of the Annual ACM Conference on Computational Learning TheoryPages 57 - 671996 Proceedings of the 1996 9th Annual Conference on Computational Learning Theory28 June 1996through 1 July 1996",

note = "Proceedings of the 1996 9th Annual Conference on Computational Learning Theory ; Conference date: 28-06-1996 Through 01-07-1996",

}

Ratsaby, J, Meir, R & Maiorov, V 1996, Towards robust model selection using estimation and approximation error bounds. in Proceedings of the Annual ACM Conference on Computational Learning TheoryPages 57 - 671996 Proceedings of the 1996 9th Annual Conference on Computational Learning Theory28 June 1996through 1 July 1996. Proceedings of the Annual ACM Conference on Computational Learning Theory, pp. 57-67, Proceedings of the 1996 9th Annual Conference on Computational Learning Theory, Desenzano del Garda, Italy, 28/06/96. https://doi.org/10.1145/238061.238069

Towards robust model selection using estimation and approximation error bounds. / Ratsaby, Joel; Meir, Ronny; Maiorov, Vitaly.
Proceedings of the Annual ACM Conference on Computational Learning TheoryPages 57 - 671996 Proceedings of the 1996 9th Annual Conference on Computational Learning Theory28 June 1996through 1 July 1996. 1996. p. 57-67 (Proceedings of the Annual ACM Conference on Computational Learning Theory).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Towards robust model selection using estimation and approximation error bounds

AU - Ratsaby, Joel

AU - Meir, Ronny

AU - Maiorov, Vitaly

PY - 1996

Y1 - 1996

N2 - One of the main problems in machine learning and statistical inference is selecting an appropriate model by which a set of data can be explained. A novel model selection criterion based on the uniform convergence of empirical processes combined with the results concerning the approximation ability of non-linear manifolds of functions is introduced. A coherent and robust framework for model selection was elucidated and a lower bound on the approximation error was established, giving a well specified sense for most functions of interest.

AB - One of the main problems in machine learning and statistical inference is selecting an appropriate model by which a set of data can be explained. A novel model selection criterion based on the uniform convergence of empirical processes combined with the results concerning the approximation ability of non-linear manifolds of functions is introduced. A coherent and robust framework for model selection was elucidated and a lower bound on the approximation error was established, giving a well specified sense for most functions of interest.

UR - https://www.scopus.com/pages/publications/0030383583

U2 - 10.1145/238061.238069

DO - 10.1145/238061.238069

M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???

AN - SCOPUS:0030383583

T3 - Proceedings of the Annual ACM Conference on Computational Learning Theory

SP - 57

EP - 67

BT - Proceedings of the Annual ACM Conference on Computational Learning TheoryPages 57 - 671996 Proceedings of the 1996 9th Annual Conference on Computational Learning Theory28 June 1996through 1 July 1996

T2 - Proceedings of the 1996 9th Annual Conference on Computational Learning Theory

Y2 - 28 June 1996 through 1 July 1996

ER -

Ratsaby J, Meir R, Maiorov V. Towards robust model selection using estimation and approximation error bounds. In Proceedings of the Annual ACM Conference on Computational Learning TheoryPages 57 - 671996 Proceedings of the 1996 9th Annual Conference on Computational Learning Theory28 June 1996through 1 July 1996. 1996. p. 57-67. (Proceedings of the Annual ACM Conference on Computational Learning Theory). doi: 10.1145/238061.238069

Towards robust model selection using estimation and approximation error bounds

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this