Statistical Seminar: Every Monday at 2:00 pm.
Time: 2:00 pm – 3:15 pm
Date: 14th of June 2021
Place: Visio
Jonathan NILES-WEED (NYU) – “The “all-or-nothing” phenomenon in sparse estimation”

Abstract: We explore a sharp phase transition known as the “all-or-nothing” phenomenon in estimation problems. This phenomenon arises when there exists a critical signal to noise ratio (SNR) such that below this threshold it is impossible to achieve any positive correlation with the hidden signal, whereas above this threshold it is possible to achieve almost perfect correlation with the hidden signal. This phenomenon has been observed in a few different models and settings, but with no unified explanation. We give a sharp characterization of this phenomenon in the presence of Gaussian noise and give general conditions under which it holds. As a corollary, we obtain the all-or-nothing phenomenon for the sparse tensor PCA, Bernoulli group testing, and the planted Gaussian perceptron problems. Joint work with Ilias Zadik.

Organizers:
Cristina BUTUCEA (CREST), Alexandre TSYBAKOV (CREST), Karim LOUNICI (CMAP) , Zoltan SZABO (CMAP)
Sponsors:
CREST-CMAP