Learning Fast-Mixing Models for Structured Prediction

  • Steinhardt J
  • Liang P
  • 47


    Mendeley users who have this article in their library.
  • 4


    Citations of this article.


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.

Get free article suggestions today

Mendeley saves you time finding and organizing research

Sign up here
Already have an account ?Sign in

Find this document


  • Jacob Steinhardt

  • Percy Liang

Cite this document

Choose a citation style from the tabs below

Save time finding and organizing research with Mendeley

Sign up for free