Learning Fast-Mixing Models for Structured Prediction

Abstract

Markov Chain Monte Carlo (MCMC) algorithms are often used for approximate inference inside learning, but their slow mixing can be difficult to diagnose and the approximations can seriously degrade learning. To alleviate these issues, we define a new model family using strong Doeblin Markov chains, whose mixing times can be precisely controlled by a… (More)
View Slides

Topics

5 Figures and Tables

Slides referencing similar topics