Event time:
Tuesday, March 21, 2017 - 12:15pm to 1:15pm
Location:
LOM 206
Speaker:
Tyler Maunu
Speaker affiliation:
University of Minnesota
Event description:
We present a mathematical analysis of a gradient descent method for Robust Subspace Recovery. The optimization is cast as a minimization over the Grassmannian manifold, and gradient steps are taken along geodesics. We show that under a generic condition, the energy landscape is nice enough for the non-convex gradient method to exactly recover an underlying subspace. The condition is shown to hold with high probability for a certain model of data.
Special note:
Non-standard location