Séminaire Probabilités et Statistiques
Difficulties and nonstandard minimax rates in nonparametric latent variable models
28
March 2024
logo_team
Intervenant : Bryon Aragam
Institution : University of Chicago
Heure : 15h45 - 16h45
Lieu : 3L15

 We revisit the statistical foundations of nonparametric latent variable models and discuss how even basic statistical properties such as identifiability and consistency are surprisingly subtle. For example, even in simple mixtures, the existence of a uniformly consistent estimator is not guaranteed. Motivated by these difficulties, we develop a uniformly consistent estimator and then characterize the optimal sample complexity for this problem, which turn out to have a nonstandard super-polynomial bound. These results are then be applied to study mixtures of nonparametric regression models. Time permitting, we will also discuss some implications of these results for learning structured representations in machine learning.

All (past and future) events