When: September 28, 2016, 12:30 PM
Location: Researchers' Link, 2nd floor of the Discovery Building
Contact: 608-316-4401, email@example.com
Speeding up Machine Learning using Graphs and Codes
I will talk about three simple combinatorial ideas to speed up parallel and distributed learning algorithms. We will start off with serial equivalence in asynchronous parallel ML, its significance, and how we can guarantee it using a recent phase transition result on graphs. We continue on the issue of stragglers (i.e., slow nodes) in distributed systems, where we will use erasure codes to robustify gradient based algorithms against delays. In our third example, we will reduce the high communication cost of data-shuffling in distributed learning, using the seemingly unrelated notion of coded caching. For all the above, we will see real world experiments that indicate how these simple ideas can significantly improve the speed and accuracy of large-scale learning.
The weekly SILO seminar series is made possible through the generous support of the 3M Company and its Advanced Technology Group
SILO is a lecture series with speakers from the UW faculty, graduate students or invited researchers that discuss mathematical related topics. The seminars are organized by WID’s Optimization research group.
SILO’s purpose is to provide a forum that helps connect and recruit mathematically-minded graduate students. SILO is a lunch-and-listen format, where speakers present interesting math topics while the audience eats lunch.