Statistical Foundations of Latent Structure and Representation Learning

About

Modern statistical and machine learning problems increasingly rely on uncovering latent structure and learning informative representations from complex, high-dimensional data. Fundamental questions concerning identifiability, statistical efficiency, uncertainty quantification, computation, causality, and interpretability arise across latent variable models, high-dimensional statistics, networks, and modern representation learning.

This two-day workshop brings together researchers from statistics, machine learning, data science, and related fields to discuss recent advances and emerging connections in the statistical foundations of latent structure and representation learning.