Main Profile

At A Glance

NIPS 2011 Big Learning - Algorithms, Systems, & Tools Workshop: Large-Scale Matrix...

Big Learning Workshop: Algorithms, Systems, and Tools for Learning at Scale at NIPS 2011 Invited Talk: Large-Scale Matrix Factorization with Distributed Stochastic Gradient Descent by Rainer Gemulla Rainer Gemulla graduated from the Technische Universit?t Dresden in Germany in the area of database sampling. He is currently working as a senior researcher at the Max-Plack-Institut f?r Informatik in Saarbr?cken, Germany. Abstract: We provide a novel algorithm to approximately factor large matrices with millions of rows, millions of columns, and billions of nonzero elements. Our approach rests on stochastic gradient descent (SGD), an iterative stochastic optimization algorithm. Based on a novel "stratified'' variant of SGD, we obtain a new matrix-factorization algorithm, called DSGD, that can be fully distributed and run on web-scale datasets using, e.g., MapReduce. DSGD can handle a wide variety of matrix factorizations and has good scalability properties.
Length: 20:10

Contact

Questions about NIPS 2011 Big Learning - Algorithms, Systems, & Tools Workshop: Large-Scale Matrix...

Want more info about NIPS 2011 Big Learning - Algorithms, Systems, & Tools Workshop: Large-Scale Matrix...? Get free advice from education experts and Noodle community members.

  • Answer

Ask a New Question