To Relieve Your Headache of Training an MRF, Take AdVIL

2019/01/24 by Chongxuan Li, Li, Chongxuan, Chao Du +9 · 1 citation
Computer Science · #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Gaussian Processes and Bayesian Inference #Generative Adversarial Networks and Image Synthesis #Machine Learning (cs.LG) #Machine Learning (stat.ML)

paper · pdf · doi:10.48550/arxiv.1901.08400

openalex publication_date 2019/01/24 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

We propose a black-box algorithm called \it Adversarial Variational Inference and Learning (AdVIL) to perform inference and learning on a general Markov random field (MRF). AdVIL employs two variational distributions to approximately infer the latent variables and estimate the partition function of an MRF, respectively. The two variational distributions provide an estimate of the negative log-likelihood of the MRF as a minimax optimization problem, which is solved by stochastic gradient descent. AdVIL is proven convergent under certain conditions. On one hand, compared with contrastive divergence, AdVIL requires a minimal assumption about the model structure and can deal with a broader family of MRFs. On the other hand, compared with existing black-box methods, AdVIL provides a tighter estimate of the log partition function and achieves much better empirical results.

Citations

• Annealed importance sampling
• Adam: A Method for Stochastic Optimization
• Gradient Estimation Using Stochastic Computation Graphs
• Stochastic Backpropagation and Approximate Inference in Deep Generative\n Models
• Training Products of Experts by Minimizing Contrastive Divergence
• Adversarial Feature Learning
• Categorical Reparameterization with Gumbel-Softmax
• Generative Adversarial Networks as Variational Training of Energy Based Models
• A Connection between Generative Adversarial Networks, Inverse Reinforcement Learning, and Energy-Based Models
• TensorFlow: A system for large-scale machine learning

Cited by

• Bi-level Score Matching for Learning Energy-based Latent Variable Models

Related

• MCMC Learning
• On Learning Continuous Pairwise Markov Random Fields
• Structure Learning of Markov Random Fields through Grow-Shrink Maximum Pseudolikelihood Estimation
• A Latent-Variable Lattice Model
• A new class of Markov random fields enabling lightweight sampling