Authors: Schwiegelshohn, Chris
Sohler, Christian
Title: Logistic Regression in Datastreams
Language (ISO): en
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.
URI: http://hdl.handle.net/2003/37168
http://dx.doi.org/10.17877/DE290R-19164
Issue Date: 2014-01
Appears in Collections:Sonderforschungsbereich (SFB) 876

Files in This Item:
File Description SizeFormat 
schwiegelshohn_sohler_2014a.pdfDNB354.08 kBAdobe PDFView/Open


This item is protected by original copyright



Items in Eldorado are protected by copyright, with all rights reserved, unless otherwise indicated.