A unified framework shows that NCE, RLR, MIS, and bridge sampling are equivalent under specific conditions for energy-based models, enabling new estimators.
Importance sampling and contrastive learning schemes for parameter estimation in non-normalized models
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CE 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
A unifying view of contrastive learning, importance sampling, and bridge sampling for energy-based models
A unified framework shows that NCE, RLR, MIS, and bridge sampling are equivalent under specific conditions for energy-based models, enabling new estimators.