LIR unifies EM, belief propagation, adversarial training, GANs, and GFlowNets as instances of local inconsistency resolution on Probabilistic Dependency Graphs and demonstrates a better GFlowNet loss on synthetic data.
Conditional Probability DistributionsFor each edge( i→j ) ∈ A , we assign a randomly initialized conditional probability tablePij(Xj|Xi)drawn uniformly from the probability simplex
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Local Inconsistency Resolution: The Interplay between Attention and Control in Probabilistic Models
LIR unifies EM, belief propagation, adversarial training, GANs, and GFlowNets as instances of local inconsistency resolution on Probabilistic Dependency Graphs and demonstrates a better GFlowNet loss on synthetic data.