[Ml-stat-talks] Fwd: PACM Colloquium

Elad Hazan ehazan at CS.Princeton.EDU
Tue Mar 22 22:50:09 EDT 2016


Talk of interest on Monday.



*PACM Colloquium - March 28, 2016*



*Speaker:    Ankur Moitra, MIT*



*Title:   Beyond Matrix Completion *



*Abstract:*  Here we study some of the statistical and algorithmic problems
that arise in recommendation systems. We will be interested in what happens
when we move beyond the matrix setting, to work with higher order objects —
namely, tensors. To what extent does inference over more complex objects
yield better predictions, but at the expense of the running time? We will
explore the computational vs. statistical tradeoffs for some basic problems
about recovering approximately low rank tensors from few observations, and
will show that our algorithms are nearly optimal among all polynomial time
algorithms, under natural complexity-theoretic assumptions.



This is based on joint work with Boaz Barak.





Thanks,



Liz Van Dzura

Faculty Assistant, Temp

Princeton University

PACM ~ Program in Applied & Computational Mathematics

203 Fine Hall, Washington Rd, Princeton, NJ 08544

609-258-3703

ldzura at princeton.edu
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.cs.princeton.edu/pipermail/ml-stat-talks/attachments/20160322/5ca6441e/attachment.html>


More information about the Ml-stat-talks mailing list