Amortized Bethe Free Energy Minimization for Learning MRFs

Sam Wiseman, Yoon Kim

Jan-27-2025, 12:51:52 GMT–Neural Information Processing Systems

We propose to learn deep undirected graphical models (i.e., MRFs) with a non-ELBO objective for which we can calculate exact gradients.

artificial intelligence, machine learning, natural language, (19 more...)

Neural Information Processing Systems

Jan-27-2025, 12:51:52 GMT

Conferences PDF

Country:
- North America > United States > Illinois (0.14)

Industry:
- Education (0.46)

Technology:
- Information Technology > Artificial Intelligence
  - Machine Learning
    - Learning Graphical Models
      - Directed Networks > Bayesian Learning (0.46)
      - Undirected Networks > Markov Models (0.69)
    - Neural Networks > Deep Learning (1.00)
  - Natural Language (0.94)
  - Representation & Reasoning (1.00)