Learning Fast-Mixing Models for Structured Prediction

Code

• worksheets.codalab.org/worksheets/0xc6edf0c9bec643ac9e74418bd6ad4136
  Officialnone★ 0

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 parameter. We also develop an algorithm to learn such models, which involves maximizing the data likelihood under the induced stationary distribution of these chains. We show empirical improvements on two challenging inference tasks.

Tasks

Reproductions