[AI Seminar] AI Lunch -- Po-Wei Wang -- January 31

[Adams Wei Yu]

Dear faculty and students,

We look forward to seeing you Next Tuesday, January 31, at noon in NSH 3305
for AI lunch. To learn more about the seminar and lunch, please visit
the AI Lunch webpage <http://www.cs.cmu.edu/~aiseminar/>.

On Tuesday, Po-Wei Wang <http://www.powei.tw/> will give a talk titled
“Polynomial optimization methods for matrix factorization”.

*Abstract:* Matrix factorization is a core technique in many machine
learning problems, yet also presents a nonconvex and often
difficult-to-optimize problem. In this paper we present an approach based
upon polynomial optimization techniques that both improves the convergence
time of matrix factorization algorithms and helps them escape from local
optima. Our method is based on the realization that given a joint search
direction in a matrix factorization task, we can solve the ``subspace
search'' problem (the task of jointly finding the steps to take in each
direction) by solving a bivariate quartic polynomial optimization problem.
We derive two methods for solving this problem based upon sum of squares
moment relaxations and the Durand-Kerner method, then apply these
techniques on matrix factorization to derive a direct coordinate descent
approach and a method for speeding up existing approaches. On three
benchmark datasets we show the method substantially improves convergence
speed over state-of-the-art approaches, while also attaining lower
objective value.

This is a joint work with Chun-Liang Li and J. Zico Kolter. Forthcoming in
AAAI 2017.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/ai-seminar-announce/attachments/20170127/27133949/attachment.html>