Semidefinite relaxation for deep ReLU verification suffers from 'interior-point vanishing' as depth increases, and removing layer-wise bound constraints mitigates it.
Efficient Neural Network Verification via Layer-Based Semidefinite Relaxations and Linear Cuts
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
support 1representative citing papers
citing papers explorer
-
Interior-Point Vanishing Problem in Semidefinite Relaxations for Neural Network Verification
Semidefinite relaxation for deep ReLU verification suffers from 'interior-point vanishing' as depth increases, and removing layer-wise bound constraints mitigates it.