Probability Seminar

Date: March 29, 2019

Time: 11:00AM - 12:00PM

Location: BLOC 628

Speaker: Wei-Kuo Chen, University of Minnesota

Title: Phase Transition in the Spiked Gaussian Tensor Models

Abstract: The problem of detecting a deformation in a symmetric Gaussian random tensor is concerned about whether there exists a statistical hypothesis test that can reliably distinguish a low-rank random spike from the noise. In this talk, we will consider the spikes sampled from bounded priors. We will show that there exist critical thresholds for the signal-to-noise ratios, which strictly separate the distinguishability and indistinguishability between the non-spiked and spiked Gaussian random tensors under the total variation distance. Our approach is based on a subtle analysis of the high temperature behavior of the pure p-spin model, arising initially from the field of spin glasses. In particular, the signal-to-noise criticality is identified as the critical temperature, distinguishing the high and low temperature behavior, of the pure p-spin model.