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.
Neural network verification with branch-and-bound for general nonlinearities
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
verdicts
UNVERDICTED 3representative citing papers
CT-BaB integrates branch-and-bound during training to tighten certified Lyapunov bounds, yielding neural controllers with 164X larger verifiable ROA and 11X faster verification than CEGIS on a 2D quadrotor.
Introduces partial multi-neuron relaxation using existing branching heuristics to balance bound tightness and scalability in neural network verification, with integration into Marabou showing positive experimental comparisons.
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.
-
Neural Network Verification using Partial Multi-Neuron Relaxation
Introduces partial multi-neuron relaxation using existing branching heuristics to balance bound tightness and scalability in neural network verification, with integration into Marabou showing positive experimental comparisons.