资源分类
》 资源 》论文》Learning Fast-Mixing Models for Structured Prediction

Learning Fast-Mixing Models for Structured Prediction

2020-03-05 | |  84 |   46 |   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 resulting approximate gradients 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 inference tasks.

上一篇：Sparse Variational Inference for Generalized Gaussian Process Models

下一篇：Adaptive Stochastic Alternating Direction Method of Multipliers

用户评价
全部评价

热门资源

  • The Variational S...

    Unlike traditional images which do not offer in...

  • Learning to Predi...

    Much of model-based reinforcement learning invo...

  • Stratified Strate...

    In this paper we introduce Stratified Strategy ...

  • Learning to learn...

    The move from hand-designed features to learned...

  • A Mathematical Mo...

    Direct democracy, where each voter casts one vo...