Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Schwiegelshohn, Chris | - |
dc.contributor.author | Sohler, Christian | - |
dc.date.accessioned | 2018-10-12T08:23:06Z | - |
dc.date.available | 2018-10-12T08:23:06Z | - |
dc.date.issued | 2014-01 | - |
dc.identifier.uri | http://hdl.handle.net/2003/37168 | - |
dc.identifier.uri | http://dx.doi.org/10.17877/DE290R-19164 | - |
dc.description.abstract | Learning from data streams is a well researched task both in theory and practice. As remarked by Clarkson, Hazan and Woodruff, many classification problems cannot be very well solved in a streaming setting. For previous model assumptions, there exist simple, yet highly artificial lower bounds prohibiting space efficient one- pass algorithms. At the same time, several classification algorithms are often successfully used in practice. To overcome this gap, we give a model relaxing the constraints that previously made classification impossible from a theoretical point of view and under these model assumptions provide the first (1 + epsilon) -approximate algorithms for sketching the objective values of logistic regression and perceptron classifiers in data streams. | en |
dc.language.iso | en | de |
dc.relation.ispartofseries | Technical report / Sonderforschungsbereich Verfügbarkeit von Information durch Analyse unter Ressourcenbeschränkung;1/2014 | en |
dc.subject.ddc | 004 | - |
dc.title | Logistic Regression in Datastreams | en |
dc.type | Text | de |
dc.type.publicationtype | report | de |
dcterms.accessRights | open access | - |
eldorado.secondarypublication | false | de |
Appears in Collections: | Sonderforschungsbereich (SFB) 876 |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
schwiegelshohn_sohler_2014a.pdf | DNB | 354.08 kB | Adobe PDF | View/Open |
This item is protected by original copyright |
This item is protected by original copyright rightsstatements.org