This was part of Algebraic Statistics for Ecological and Biological Systems

Maximum likelihood thresholds of Gaussian models via rigidity theory

Daniel Bernstein, Tulane University

Friday, October 13, 2023

Abstract: The maximum likelihood threshold (MLT) of a statistical model is the minimum number of datapoints require to almost surely guarantee existence of a maximum likelihood estimator.  This talk will discuss recent results, obtained using rigidity-theoretic methods, about MLTs of Gaussian models including Gaussian graphical models and linear concentration models.