Score-augmented loss functions for neural likelihood surrogates in SBI deliver downstream inference performance equivalent to 10x more training data at under 1.1x training time cost on network and spatial process models.
Curran Associates Inc., Red Hook, NY , USA
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Neural networks learn to construct argumentation structures that explain classifications through support and attack relations, trained jointly with differentiable semantics and structure constraints.
citing papers explorer
-
Keeping Score: Efficiency Improvements in Neural Likelihood Surrogate Training via Score-Augmented Loss Functions
Score-augmented loss functions for neural likelihood surrogates in SBI deliver downstream inference performance equivalent to 10x more training data at under 1.1x training time cost on network and spatial process models.
-
Deep Arguing
Neural networks learn to construct argumentation structures that explain classifications through support and attack relations, trained jointly with differentiable semantics and structure constraints.