Proves that the connectivity graph of linear regions in fully-connected ReLU networks has average degree ≤ 2×input dimension and diameter bounded independently of input dimension.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
STBP computes exact closed-form bounds for the first convolutional layer of spatio-temporal networks and propagates scalable approximations through the rest to certify robustness under subset-frame or patch perturbations.
citing papers explorer
-
Characterizing the Discrete Geometry of ReLU Networks
Proves that the connectivity graph of linear regions in fully-connected ReLU networks has average degree ≤ 2×input dimension and diameter bounded independently of input dimension.
-
Hybrid Robustness Verification for Spatio-Temporal Neural Networks
STBP computes exact closed-form bounds for the first convolutional layer of spatio-temporal networks and propagates scalable approximations through the rest to certify robustness under subset-frame or patch perturbations.