NIPS 2011 Big Learning - Algorithms, Systems, & Tools Workshop: Large-Scale Matrix...
2,061 views · Published 14 February 2012 · 20:10 · Indexed 6 November 2026
Channel: Google TechTalks · 2012 · Science & Technology
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 Universität Dresden in Germany in the area of database sampling. He is currently working as a senior researcher at the Max-Plack-Institut für Informatik in Saarbrücken, 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.
More from this channel
-
34:17
Thinglink - A Free Product Code for Creative Work
-
32:48
Thinking Beyond Borders
-
44:29
Understanding Urban Environments Through the Use of...
-
46:05
Customer Centric Web Decision Making
-
46:04
Customizable Scalable Compute Intensive Stream Queries
-
51:26
All The Government's Information
-
41:35
Combining Discriminative Features to Infer Complex...
-
59:42
Dimensions of Reputation in Electronic Markets