Local Convergence of GROUSE | Multiplicative-forest continuous-time disease prediction from Electronic Health Records
Profesor Wright’s abstract: GROUSE is an incremental algorithm for subspace identification based on incomplete information, proposed and studied by Laura Balzano, Rob Nowak, and Ben Recht at Madison. This talk discusses recent results on the local convergence behavior of GROUSE, showing an expected linear convergence rate. Stronger results are possible …