Free ACM Talk : Data Mining SIG - Learning Outside the Box and the Simplex: Efficient Projection Algorithms for Sparse Representations April 9, 2008

Data Mining SIG
San Francisco Bay Area Chapter of ACM (http://www.sfbayacm.org)

Topic: Learning Outside the Box and the Simplex: Efficient Projection Algorithms for Sparse Representations

Speaker: Yoram Singer, Senior Research Scientist, Google Inc.

Please RSVP at [email protected] if you plan to attend.

Topic Summary
Many problems in machine learning are cast as constrained optimization problems. The talk focuses on efficient algorithms for learning tasks which are cast as optimization problems subject to L1 and box constraints. The end result are typically sparse and accurate models. We start with an overview of existing projection algorithms onto the simplex. We then describe a linear time projection for dense input spaces. Finally, we describe a new efficient projection algorithm for very high dimensional spaces. We demonstrate the merits of the algorithm in experiments with image and large scale text classification.

About the Speaker
Yoram Singer is a senior research scientist at Google Inc. From 1999 through 2007 he was an associate professor of computer science at the Hebrew University, Jerusalem, Israel. From 1995 through 1999 he was a member of the technical staff at AT&T Research. His work focuses on the design, analysis, and implementation of machine learning algorithms.

Official Website: http://www.sfbayacm.org/events/2008-04-09.php