mPOLICE generalizes POLICE to enforce exact affine output constraints inside multiple disjoint convex regions of a ReLU network's input by giving each region its own activation pattern.
XLB : A differentiable massively parallel lattice Boltzmann library in python
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
mPOLICE: Provable Enforcement of Multi-Region Affine Constraints in Deep Neural Networks
mPOLICE generalizes POLICE to enforce exact affine output constraints inside multiple disjoint convex regions of a ReLU network's input by giving each region its own activation pattern.