alpha_beta-CROWN
PulseAugur coverage of alpha_beta-CROWN — every cluster mentioning alpha_beta-CROWN across labs, papers, and developer communities, ranked by signal.
2 day(s) with sentiment data
-
New lookahead lemma framework enhances neural network verification
Researchers have developed a new in-processing framework for neural network verification that utilizes a lookahead procedure. This method generates new lemmas based on unstable ReLUs, which are then compiled into an imp…
-
New lookahead strategy boosts neural network verification efficiency
Researchers have developed a new lookahead branching strategy for neural network verification, aiming to improve the efficiency and effectiveness of existing branch-and-bound verifiers. This strategy can be integrated i…
-
New Veriphi System Integrates Attacks and Certification for Neural Network Verification
Researchers have developed Veriphi, a new system for verifying neural networks that integrates fast adversarial attacks with formal bound certification. Experiments on MNIST and CIFAR-10 datasets revealed that the effec…
-
AI verification scales with new parallelism techniques
Researchers have adapted tensor parallelism and fully sharded data parallelism techniques, typically used for training large models, to improve the scalability of neural network verification. These methods address the G…
-
Neural Network Verifier alpha-beta-CROWN Enhances Control Synthesis Safety
Researchers have developed a unified framework to bridge neural network verification with control synthesis, aiming to improve safety in critical systems. The approach utilizes the alpha-beta-CROWN neural network verifi…