[Ml-stat-talks] Fwd: Colloquium Speaker Nati Srebro, Thrusday March 12, 4:30pm

Elad Hazan ehazan at CS.Princeton.EDU
Thu Mar 12 00:17:57 EDT 2015


Talk of interest to stats/ML below.

Best,
Elad




---------- Forwarded message ----------


CSML/CS Colloquium Speaker
Nati Srebro
Thursday, March 12, 4:30pm
Computer Science 105

The Power of Asymmetry in Binary Hashing

When looking for similar objects, like images and documents, and
especially when querying a large remote data-base for similar objects,
it is often useful to construct short similarity-preserving binary
hashes. That is, to map each image or document to a short bit strings
such that similar objects have similar bit strings. Such a mapping
lies at the root of nearest neighbor search methods such as Locality
Sensitive Hashing (LSH) and is recently gaining popularity in a
variety of vision, image retrieval and document retrieval
applications. In this talk I will demonstrate, both theoretically and
empirically, that even for symmetric and well behaved similarity
measures, much could be gained by using two different hash
functions---one for hashing objects in the database and an entirely
different hash function for the queries. Such asymmetric hashings can
allow to significantly shorter bit strings and more accurate
retrieval.

Joint work with Behnam Neyshabur, Yury Makarychev and Russ Salakhutdinov


Nati Srebro obtained his PhD at the Massachusetts Institute of
Technology (MIT) in 2004, held a post-doctoral fellowship with the
Machine Learning Group at the University of Toronto, and was a
Visiting Scientist at IBM Haifa Research Labs.  Since January 2006, he
has been on the faculty of the Toyota Technological Institute at
Chicago (TTIC) and the University of Chicago, and has also served as
the first Director of Graduate Studies at TTIC.  From 2013 to 2014 he
was associate professor at the Technion-Israel Institute of
Technology. Prof. Srebro's research encompasses methodological,
statistical and computational aspects of Machine Learning, as well as
related problems in Optimization.  Some of Prof. Srebro's significant
contributions include work on learning "wider" Markov networks,
pioneering work on matrix factorization and collaborative prediction,
including introducing the use of the nuclear norm for machine learning
and matrix reconstruction and work on fast optimization techniques for
machine learning, and on the relationship between learning and
optimization.


More information about the Ml-stat-talks mailing list