AKSW Colloquium, 21.03.2016, Quit-Store a quad store versioned with git + Distributed methods for Stochastic Gradient Descent

On the 21th of March a 3 PM, Norman Radtke will present his current work at LEDS project: the Quit-Store.

The Quit-Store is an in-memory quad store with git versioning. The store accepts SPARQL Select and Update queries. After an execution of a SPARQL Update the store will commit all changes of all named graphes. Therefor each named graphs is represented in a file containing alphabetically ordered n-quads.

Later on, at 3:30 PM, Nilesh Chakraborty will present an overview of two state-of-the-art methods for running stochastic gradient descent in a distributed setting.

The two papers are “SCOPE: Scalable Composite Optimization for Learning on Spark” by Zhao et al. and “Large-Scale Matrix Factorization with Distributed Stochastic Gradient Descent” by Gemulla et al.

About the AKSW Colloquium

This event is part of a series of events about Semantic Web technology. Please see http://wiki.aksw.org/Colloquium for further information about previous and future events. As always, Bachelor and Master students are able to get points for attendance and there is complimentary coffee and cake after the session.

This entry was posted in Colloquium and tagged , , , , . Bookmark the permalink.