Fall 2020

Phase Retrieval in High Dimensions: Statistical and Computational Phase Transitions

Tuesday, Sep. 22, 2020 10:35 am11:00 am PDT

Add to Calendar


Florent Krzakala, ENS

The increasing dimensionality of data in the modern computing age presents new challenges and opportunities to the field of signal and data processing.  Here I will present some of the results we obtained through the use of heuristics statistical mechanics as well as rigorous methods for reconstructing a signal from a minimal number of generalized linear measurements, concentrating in particular to the phase retrieval problem. I shall discuss in particular the statistical and computational transitions, as well as the role of structured priors such as the one played by neutral networks.

* Benjamin Aubin, Bruno Loureiro, Antoine Baker, Florent Krzakala, Lenka Zdeborová ; Proceedings of The First Mathematical and Scientific Machine Learning Conference, PMLR 107:55-73, 2020.
* Antoine Maillard, Bruno Loureiro, Florent Krzakala, Lenka Zdeborová, Phase retrieval in high dimensions: Statistical and computational phase transitions arXiv preprint arXiv:2006.05228