We consider the problem of estimating large rank-one matrix, given noisy observations. This inference problem is known to have a phase transition, in the sense that partial recovery of the original matrix is only possible if the signal-to-noise ratio exceeds a (non-zero) value. We will present a new proof of this fact based on the study of a Hamilton-Jacobi equation. This alternative argument allows one to obtain better rates of convergence, and also seems more amenable to extensions to other models such as spin glasses
Additional Information
Please contact organizers for meeting ID at mathav@math.ubc.ca Jean-Christoph Mourrat, NYU