File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1016/j.neucom.2017.11.049
- Scopus: eid_2-s2.0-85037056507
- WOS: WOS:000418370200245
- Find via
Supplementary
- Citations:
- Appears in Collections:
Article: Refined bounds for online pairwise learning algorithms
Title | Refined bounds for online pairwise learning algorithms |
---|---|
Authors | |
Keywords | Learning theory Online learning Pairwise learning Reproducing Kernel Hilbert Space |
Issue Date | 2018 |
Citation | Neurocomputing, 2018, v. 275, p. 2656-2665 How to Cite? |
Abstract | Motivated by the recent growing interest in pairwise learning problems, we study the generalization performance of Online Pairwise lEaRning Algorithm (OPERA) in a reproducing kernel Hilbert space (RKHS) without an explicit regularization. The convergence rates established in this paper can be arbitrarily closed to O(T−[Formula presented]) within T iterations and largely improve the existing convergence rates for OPERA. Our novel analysis is conducted by showing an almost boundedness of the iterates encountered in the learning process with high probability after establishing an induction lemma on refining the RKHS norm estimate of the iterates. |
Persistent Identifier | http://hdl.handle.net/10722/329479 |
ISSN | 2023 Impact Factor: 5.5 2023 SCImago Journal Rankings: 1.815 |
ISI Accession Number ID |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Chen, Xiaming | - |
dc.contributor.author | Lei, Yunwen | - |
dc.date.accessioned | 2023-08-09T03:33:05Z | - |
dc.date.available | 2023-08-09T03:33:05Z | - |
dc.date.issued | 2018 | - |
dc.identifier.citation | Neurocomputing, 2018, v. 275, p. 2656-2665 | - |
dc.identifier.issn | 0925-2312 | - |
dc.identifier.uri | http://hdl.handle.net/10722/329479 | - |
dc.description.abstract | Motivated by the recent growing interest in pairwise learning problems, we study the generalization performance of Online Pairwise lEaRning Algorithm (OPERA) in a reproducing kernel Hilbert space (RKHS) without an explicit regularization. The convergence rates established in this paper can be arbitrarily closed to O(T−[Formula presented]) within T iterations and largely improve the existing convergence rates for OPERA. Our novel analysis is conducted by showing an almost boundedness of the iterates encountered in the learning process with high probability after establishing an induction lemma on refining the RKHS norm estimate of the iterates. | - |
dc.language | eng | - |
dc.relation.ispartof | Neurocomputing | - |
dc.subject | Learning theory | - |
dc.subject | Online learning | - |
dc.subject | Pairwise learning | - |
dc.subject | Reproducing Kernel Hilbert Space | - |
dc.title | Refined bounds for online pairwise learning algorithms | - |
dc.type | Article | - |
dc.description.nature | link_to_subscribed_fulltext | - |
dc.identifier.doi | 10.1016/j.neucom.2017.11.049 | - |
dc.identifier.scopus | eid_2-s2.0-85037056507 | - |
dc.identifier.volume | 275 | - |
dc.identifier.spage | 2656 | - |
dc.identifier.epage | 2665 | - |
dc.identifier.eissn | 1872-8286 | - |
dc.identifier.isi | WOS:000418370200245 | - |