QLL is a novel logic for neuro-symbolic learning that uses ML-native operations (sum, log-sum-exp) on logits to embed constraints, satisfying most linear logic properties and showing stronger correlation between empirical robustness and formal verification than prior approaches.
2 Ross Anderson, Joey Huchette, Will Ma, Christian Tjandraatmadja, and Juan Pablo Vielma
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
verdicts
UNVERDICTED 3roles
background 1polarities
background 1representative citing papers
MLSkip demonstrates that lightweight metadata enables data skipping for ReLU-based ML filters, with 27.4% average pruning using min-max and 38.31% using 2D convex hulls on TPC benchmarks, for a 1.07x end-to-end speedup.
FaVeX accelerates verified explanations for neural networks via dynamic batch-sequential processing and query reuse while introducing verifier-optimal robust explanations that incorporate verifier incompleteness.
citing papers explorer
-
Quantitative Linear Logic for Neuro-Symbolic Learning and Verification
QLL is a novel logic for neuro-symbolic learning that uses ML-native operations (sum, log-sum-exp) on logits to embed constraints, satisfying most linear logic properties and showing stronger correlation between empirical robustness and formal verification than prior approaches.
-
MLSkip: Data Skipping for ML Filters via Lightweight Metadata
MLSkip demonstrates that lightweight metadata enables data skipping for ReLU-based ML filters, with 27.4% average pruning using min-max and 38.31% using 2D convex hulls on TPC benchmarks, for a 1.07x end-to-end speedup.
-
Faster Verified Explanations for Neural Networks
FaVeX accelerates verified explanations for neural networks via dynamic batch-sequential processing and query reuse while introducing verifier-optimal robust explanations that incorporate verifier incompleteness.