Authors: Bockermann, Christian
Lee, Sangkyun
Title: Scalable stochastic gradient descent with improved confidence
Language (ISO): en
Abstract: Stochastic gradient descent methods have been quite successful for solving large- scale and online learning problems. We provide a simple parallel framework to obtain solutions of high confidence, where the confidence can be easily controlled by the number of processes, independently of the length of learning processes. Our framework is implemented as a scalable open-source software which can be configured for a single multicore machine or for a cluster of computers, where the training outcomes from independent parallel processes are combined to produce the final output.
URI: http://hdl.handle.net/2003/29345
http://dx.doi.org/10.17877/DE290R-3293
Issue Date: 2012-02-28
Is part of: NIPS Workshop on Big Learning -- Algorithms, Systems, and Tools for Learning at Scale
Appears in Collections:Sonderforschungsbereich (SFB) 876

Files in This Item:
File Description SizeFormat 
lee_bockermann_2011a_2.pdfDNB185.65 kBAdobe PDFView/Open


This item is protected by original copyright



All resources in the repository are protected by copyright.