To Relieve Your Headache of Training an MRF, Take AdVIL
arXiv:1901.08400
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.
References in corpus (15)
- Adam: A Method for Stochastic Optimization
- TensorFlow: A system for large-scale machine learning
- GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
- Categorical Reparameterization with Gumbel-Softmax
- Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials
- Stochastic Backpropagation and Approximate Inference in Deep Generative Models
- The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables
- Adversarial Feature Learning
- Adversarially Learned Inference
- Identifying and attacking the saddle point problem in high-dimensional non-convex optimization
- A Connection between Generative Adversarial Networks, Inverse Reinforcement Learning, and Energy-Based Models
- Gradient Estimation Using Stochastic Computation Graphs
- Deep Directed Generative Models with Energy-Based Probability Estimation
- Generative Adversarial Networks as Variational Training of Energy Based Models
- Learning Deep Energy Models: Contrastive Divergence vs. Amortized MLE