Learning Bounds of ERM Principle for Sequences of Time-Dependent Samples
Many generalization results in learning theory are established under the assumption that samples are independent and identically distributed (i.i.d.). However, numerous learning tasks in practical applications involve the time-dependent data. In this paper, we propose a theoretical framework to anal...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2015-01-01
|
| Series: | Discrete Dynamics in Nature and Society |
| Online Access: | http://dx.doi.org/10.1155/2015/826812 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832547478774218752 |
|---|---|
| author | Mingchen Yao Chao Zhang Wei Wu |
| author_facet | Mingchen Yao Chao Zhang Wei Wu |
| author_sort | Mingchen Yao |
| collection | DOAJ |
| description | Many generalization results in learning theory are established under the assumption that samples are independent and identically distributed (i.i.d.). However, numerous learning tasks in practical applications involve the time-dependent data. In this paper, we propose a theoretical framework to analyze the generalization performance of the empirical risk minimization (ERM) principle for sequences of time-dependent samples (TDS). In particular, we first present the generalization bound of ERM principle for TDS. By introducing some auxiliary quantities, we also give a further analysis of the generalization properties and the asymptotical behaviors of ERM principle for TDS. |
| format | Article |
| id | doaj-art-094c7b750f99473da02127b1dd29e202 |
| institution | Kabale University |
| issn | 1026-0226 1607-887X |
| language | English |
| publishDate | 2015-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Discrete Dynamics in Nature and Society |
| spelling | doaj-art-094c7b750f99473da02127b1dd29e2022025-02-03T06:44:35ZengWileyDiscrete Dynamics in Nature and Society1026-02261607-887X2015-01-01201510.1155/2015/826812826812Learning Bounds of ERM Principle for Sequences of Time-Dependent SamplesMingchen Yao0Chao Zhang1Wei Wu2School of Mathematical Sciences, Dalian University of Technology, Dalian, Liaoning 116024, ChinaSchool of Mathematical Sciences, Dalian University of Technology, Dalian, Liaoning 116024, ChinaSchool of Mathematical Sciences, Dalian University of Technology, Dalian, Liaoning 116024, ChinaMany generalization results in learning theory are established under the assumption that samples are independent and identically distributed (i.i.d.). However, numerous learning tasks in practical applications involve the time-dependent data. In this paper, we propose a theoretical framework to analyze the generalization performance of the empirical risk minimization (ERM) principle for sequences of time-dependent samples (TDS). In particular, we first present the generalization bound of ERM principle for TDS. By introducing some auxiliary quantities, we also give a further analysis of the generalization properties and the asymptotical behaviors of ERM principle for TDS.http://dx.doi.org/10.1155/2015/826812 |
| spellingShingle | Mingchen Yao Chao Zhang Wei Wu Learning Bounds of ERM Principle for Sequences of Time-Dependent Samples Discrete Dynamics in Nature and Society |
| title | Learning Bounds of ERM Principle for Sequences of Time-Dependent Samples |
| title_full | Learning Bounds of ERM Principle for Sequences of Time-Dependent Samples |
| title_fullStr | Learning Bounds of ERM Principle for Sequences of Time-Dependent Samples |
| title_full_unstemmed | Learning Bounds of ERM Principle for Sequences of Time-Dependent Samples |
| title_short | Learning Bounds of ERM Principle for Sequences of Time-Dependent Samples |
| title_sort | learning bounds of erm principle for sequences of time dependent samples |
| url | http://dx.doi.org/10.1155/2015/826812 |
| work_keys_str_mv | AT mingchenyao learningboundsofermprincipleforsequencesoftimedependentsamples AT chaozhang learningboundsofermprincipleforsequencesoftimedependentsamples AT weiwu learningboundsofermprincipleforsequencesoftimedependentsamples |