article

On the sample complexity of noise-tolerant learning

Authors:

Javed A. Aslam,

Scott E. DecaturAuthors Info & Claims

Information Processing Letters, Volume 57, Issue 4

Pages 189 - 195

https://doi.org/10.1016/0020-0190(96)00006-3

Published: 26 February 1996 Publication History

Abstract

No abstract available.

Cited By

View all

Tekumalla RBanda J(2023)Using weak supervision to generate training datasets from social media data: a proof of concept to identify drug mentionsNeural Computing and Applications10.1007/s00521-021-06614-235:25(18161-18169)Online publication date: 1-Sep-2023
https://dl.acm.org/doi/10.1007/s00521-021-06614-2
Hara SNitanda AMaehara TWallach HLarochelle HBeygelzimer Ad'Alché-Buc FFox E(2019)Data cleansing for models trained with SGDProceedings of the 33rd International Conference on Neural Information Processing Systems10.5555/3454287.3454666(4213-4222)Online publication date: 8-Dec-2019
https://dl.acm.org/doi/10.5555/3454287.3454666
Zhang ZZhao PJiang YZhou ZTeredesai AKumar VLi YRosales RTerzi EKarypis G(2019)Learning from Incomplete and Inaccurate SupervisionProceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining10.1145/3292500.3330902(1017-1025)Online publication date: 25-Jul-2019
https://dl.acm.org/doi/10.1145/3292500.3330902
Show More Cited By

Index Terms

On the sample complexity of noise-tolerant learning
1. Computing methodologies
  1. Machine learning
2. Theory of computation
  1. Computational complexity and cryptography
    1. Complexity classes

Recommendations

Computational Sample Complexity

In a variety of PAC learning models, a trade-off between time and information seems to exist: with unlimited time, a small amount of information suffices, but with time restrictions, more information sometimes seems to be required. In addition, it has ...
Efficient noise-tolerant learning from statistical queries

In this paper, we study the problem of learning in the presence of classification noise in the probabilistic learning model of Valiant and its variants. In order to identify the class of “robust” learning algorithms in the most general way, we formalize ...
Toward Efficient Agnostic Learning
Special issue on computational learning theory, COLT'92

In this paper we initiate an investigation of generalizations of the Probably Approximately Correct (PAC) learning model that attempt to significantly weaken the target function assumptions. The ultimate goal in this direction is informally termed ...

Comments

Information & Contributors

Information

Published In

Information Processing Letters Volume 57, Issue 4

Feb. 26, 1996

50 pages

ISSN:0020-0190

Editors:
F. Dehne
Carleton Univ., Ottowa, Ont., Canada
,
D. Gries
Cornell Univ., Ithaca, NY
,
W. M. Turski
Warsaw Univ., Warsaw, Poland

Issue’s Table of Contents

Publisher

Elsevier North-Holland, Inc.

United States

Publication History

Published: 26 February 1996

Author Tags

Qualifiers

Article

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

14
Total Citations
View Citations
0
Total Downloads

Downloads (Last 12 months)0
Downloads (Last 6 weeks)0

Reflects downloads up to 26 Jul 2024

Other Metrics

View Author Metrics

Citations

Cited By

View all

Tekumalla RBanda J(2023)Using weak supervision to generate training datasets from social media data: a proof of concept to identify drug mentionsNeural Computing and Applications10.1007/s00521-021-06614-235:25(18161-18169)Online publication date: 1-Sep-2023
https://dl.acm.org/doi/10.1007/s00521-021-06614-2
Hara SNitanda AMaehara TWallach HLarochelle HBeygelzimer Ad'Alché-Buc FFox E(2019)Data cleansing for models trained with SGDProceedings of the 33rd International Conference on Neural Information Processing Systems10.5555/3454287.3454666(4213-4222)Online publication date: 8-Dec-2019
https://dl.acm.org/doi/10.5555/3454287.3454666
Zhang ZZhao PJiang YZhou ZTeredesai AKumar VLi YRosales RTerzi EKarypis G(2019)Learning from Incomplete and Inaccurate SupervisionProceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining10.1145/3292500.3330902(1017-1025)Online publication date: 25-Jul-2019
https://dl.acm.org/doi/10.1145/3292500.3330902
Mikalsen KSoguero-Ruiz CBianchi FJenssen R(2019)Noisy multi-label semi-supervised dimensionality reductionPattern Recognition10.1016/j.patcog.2019.01.03390:C(257-270)Online publication date: 1-Jun-2019
https://dl.acm.org/doi/10.1016/j.patcog.2019.01.033
Van Rooyen BWilliamson R(2017)A theory of learning with corrupted labelsThe Journal of Machine Learning Research10.5555/3122009.329041318:1(8501-8550)Online publication date: 1-Jan-2017
https://dl.acm.org/doi/10.5555/3122009.3290413
Natarajan NDhillon IRavikumar PTewari A(2017)Cost-sensitive learning with noisy labelsThe Journal of Machine Learning Research10.5555/3122009.324201218:1(5666-5698)Online publication date: 1-Jan-2017
https://dl.acm.org/doi/10.5555/3122009.3242012
Natarajan NDhillon IRavikumar PTewari A(2013)Learning with noisy labelsProceedings of the 26th International Conference on Neural Information Processing Systems - Volume 110.5555/2999611.2999745(1196-1204)Online publication date: 5-Dec-2013
https://dl.acm.org/doi/10.5555/2999611.2999745
Garg DBhattacharya SSundararajan SShevade S(2012)Mechanism design for cost optimal PAC learning in the presence of strategic noisy annotatorsProceedings of the Twenty-Eighth Conference on Uncertainty in Artificial Intelligence10.5555/3020652.3020684(275-285)Online publication date: 14-Aug-2012
https://dl.acm.org/doi/10.5555/3020652.3020684
Suchanek FIfrim GWeikum GEliassi-Rad TUngar LCraven MGunopulos D(2006)Combining linguistic and statistical analysis to extract relations from web documentsProceedings of the 12th ACM SIGKDD international conference on Knowledge discovery and data mining10.1145/1150402.1150492(712-717)Online publication date: 20-Aug-2006
https://dl.acm.org/doi/10.1145/1150402.1150492
Gentile CHelmbold D(2001)Improved Lower Bounds for Learning from Noisy ExamplesInformation and Computation10.1006/inco.2000.2919166:2(133-155)Online publication date: 1-May-2001
https://dl.acm.org/doi/10.1006/inco.2000.2919
Show More Cited By

View Options

View options

Get Access

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Abstract

Cited By

Index Terms

Recommendations

Computational Sample Complexity

Efficient noise-tolerant learning from statistical queries

Toward Efficient Agnostic Learning

Comments

Information

Published In

Publisher

Publication History

Author Tags

Qualifiers

Contributors

Other Metrics

Bibliometrics

Article Metrics

Other Metrics

Citations

Cited By

View options

Get Access

Login options

Full Access

Figures

Other

Share

Share this Publication link

Share on social media

Affiliations