File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1142/S0219530515500104
- Scopus: eid_2-s2.0-84964584421
- WOS: WOS:000375088600002
- Find via
Supplementary
- Citations:
- Appears in Collections:
Article: Generalization analysis of multi-modal metric learning
Title | Generalization analysis of multi-modal metric learning |
---|---|
Authors | |
Keywords | Generalization bounds metric learning multi-modal data Rademacher complexity regularization |
Issue Date | 2016 |
Citation | Analysis and Applications, 2016, v. 14, n. 4, p. 503-521 How to Cite? |
Abstract | Multi-modal metric learning has recently received considerable attention since many real-world applications involve multi-modal data. However, there is relatively little study on the generalization analysis of the associated learning algorithms. In this paper, we bridge this theoretical gap by deriving its generalization bounds using Rademacher complexities. In particular, we establish a general Rademacher complexity result by systematically analyzing the behavior of the resulting models with various regularizers, e.g., lp-regularizer on the modality level with either a mixed (q,s)-norm or a Schatten norm on each modality. Our results and the discussion followed help to understand how the prior knowledge can be exploited by selecting an appropriate regularizer. |
Persistent Identifier | http://hdl.handle.net/10722/329402 |
ISSN | 2023 Impact Factor: 2.0 2023 SCImago Journal Rankings: 0.986 |
ISI Accession Number ID |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Lei, Yunwen | - |
dc.contributor.author | Ying, Yiming | - |
dc.date.accessioned | 2023-08-09T03:32:31Z | - |
dc.date.available | 2023-08-09T03:32:31Z | - |
dc.date.issued | 2016 | - |
dc.identifier.citation | Analysis and Applications, 2016, v. 14, n. 4, p. 503-521 | - |
dc.identifier.issn | 0219-5305 | - |
dc.identifier.uri | http://hdl.handle.net/10722/329402 | - |
dc.description.abstract | Multi-modal metric learning has recently received considerable attention since many real-world applications involve multi-modal data. However, there is relatively little study on the generalization analysis of the associated learning algorithms. In this paper, we bridge this theoretical gap by deriving its generalization bounds using Rademacher complexities. In particular, we establish a general Rademacher complexity result by systematically analyzing the behavior of the resulting models with various regularizers, e.g., lp-regularizer on the modality level with either a mixed (q,s)-norm or a Schatten norm on each modality. Our results and the discussion followed help to understand how the prior knowledge can be exploited by selecting an appropriate regularizer. | - |
dc.language | eng | - |
dc.relation.ispartof | Analysis and Applications | - |
dc.subject | Generalization bounds | - |
dc.subject | metric learning | - |
dc.subject | multi-modal data | - |
dc.subject | Rademacher complexity | - |
dc.subject | regularization | - |
dc.title | Generalization analysis of multi-modal metric learning | - |
dc.type | Article | - |
dc.description.nature | link_to_subscribed_fulltext | - |
dc.identifier.doi | 10.1142/S0219530515500104 | - |
dc.identifier.scopus | eid_2-s2.0-84964584421 | - |
dc.identifier.volume | 14 | - |
dc.identifier.issue | 4 | - |
dc.identifier.spage | 503 | - |
dc.identifier.epage | 521 | - |
dc.identifier.eissn | 1793-6861 | - |
dc.identifier.isi | WOS:000375088600002 | - |