[Ml-stat-talks] Fwd: [talks] Colloquium Speaker Ohad Shamir Tues Feb 21 4:30pm

David Blei blei at CS.Princeton.EDU
Sun Feb 19 19:28:32 EST 2012

hi ml-stat-talks

see below.  this tuesday's CS colloquium (at 4:30pm) looks excellent.
come to the second floor tea room at 4:00pm for snack and


---------- Forwarded message ----------
From: Nicole E. Wagenblast <nwagenbl at cs.princeton.edu>
Date: Fri, Feb 17, 2012 at 11:06 AM
Subject: [talks] Colloquium Speaker Ohad Shamir Tues Feb 21 4:30pm
To: "Talks (colloquium)" <talks at lists.cs.princeton.edu>

Machine Learning: Higher, Faster, Stronger
Ohad Shamir, Microsoft Research New England
Computer Science Small Auditorium (Room 105)
Tuesday, February 21, 2012, 4:30 PM - 5:30 PM

Over the past decade, machine learning has emerged as a major and
highly influential discipline of computer science and engineering. As
the scope and variety of its applications increase, it faces novel and
increasingly challenging settings, which go beyond classical learning
frameworks. In this talk, I will present two recent works which fall
under this category. The first work introduces a new model of
sequential decision making with partial information. The model
interpolates between two well-known online learning settings
("experts" and multi-armed bandits), and trades-off between the
information obtained per round and the total number of rounds required
to reach the same performance. The second work discusses the problem
of parallelizing gradient-based learning algorithms, which is
increasingly important for web-scale applications, but is highly
non-trivial as these algorithms are inherently sequential. We show how
this can be done using a generic and simple protocol, prove its
theoretical optimality, and substantiate its performance
experimentally on large-scale data.

Ohad Shamir is a postdoctoral researcher at Microsoft Research New
England. He joined Microsoft in 2010 after receiving a Ph.D. in
computer science from the Hebrew university, advised by Prof. Naftali
Tishby. His research focuses on machine learning, with emphasis on
novel algorithms which combine practical applicability and theoretical
insight. His work was recognized by several awards, such as the Hebrew
University's Schlomiuk Ph.D. thesis prize, the COLT 2010 best paper
award, and the Wolf foundation scholarship.

talks mailing list
talks at lists.cs.princeton.edu

More information about the Ml-stat-talks mailing list