October 08, 2009

"High Dimensional Nonlinear Learning using Local Coordinate Coding" (Next Week at the Statistics Seminar)

Attention conservation notice: Only of interest if you (1) care about statistical learning in high-dimensional spaces and (2) are in Pittsburgh.

Since manifold learning has been on my mind this week, owing to trying to teach it in data-mining, I am extra pleased by the scheduling of this talk:

"High Dimensional Nonlinear Learning using Local Coordinate Coding"
Prof. Tong Zhang, Rutgers University
Abstract: We present a new method for learning nonlinear functions in high dimension using semisupervised learning. Our method includes a phase of unsupervised basis learning and a phase of supervised function learning. The learned bases provide a set of anchor points to form a local coordinate system, such that each data point on a high dimensional manifold can be locally approximated by a linear combination of its nearby anchor points, with the linear weights offering its local-coordinate coding. We show that a high dimensional nonlinear function can be approximated by a global linear function with respect to this coding scheme, and the approximation quality is ensured by the locality of such coding. The method turns a difficult nonlinear learning problem into a simple global linear learning problem, which overcomes some drawbacks of traditional local learning methods. The empirical success of our approach has been demonstrated in a recent pascal image classification competition, where the top performance was achieved by an NEC system using this idea.
(Joint work with Kai Yu at NEC Lab America.)
Time and place: 4 pm on Monday, 12 October 2009, in Doherty Hall 310

As always, the seminar is free and open to the public.

Enigmas of Chance

Posted at October 08, 2009 15:01 | permanent link

Three-Toed Sloth