A Complete Decomposition of KL Error using Refined Information and Mode Interaction Selection

ArXi:2410.11964v2 Announce Type: replace The log-linear model has received a significant amount of theoretical attention in previous decades and remains the fundamental tool used for learning probability distributions over discrete variables. Despite its large popularity in statistical mechanics and high-dimensional statistics, the majority of related energy-based models only focus on the two-variable relationships, such as Boltzmann machines and Marko graphical models.