Principal component analysis with random noise

Wednesday, September 28, 2011 - 11:00am - 12:00pm
Keller 3-180
Van Vu (Yale University)
Computing the first few singular vectors of a large matrix is a problem
that frequently comes up in statistics and numerical analysis. Given the presence of noise, exact calculation is hard to achieve, and the following problem is of importance:

How much does a small perturbation to the matrix change the singular vectors ?

Answering this question, classical theorems, such as those of Davis-Kahan and Wedin, give tight estimates for the worst-case scenario.
In this paper, we show that if the perturbation (noise) is random and our matrix has low rank, then
better estimates can be obtained. Our method relies on high dimensional geometry and is different from those used an earlier studies.
MSC Code: