A complete classification of symmetries in shallow ReLU networks is achieved by using the non-differentiability of ReLU.
Geometry-Induced Implicit Regularization in Deep
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
SOC-ICNNs admit exact dual-variable recovery of first-order geometry and local Hessians as value functions of SOCPs.
citing papers explorer
-
A Complete Symmetry Classification of Shallow ReLU Networks
A complete classification of symmetries in shallow ReLU networks is achieved by using the non-differentiability of ReLU.
-
Exact Dual Geometry of SOC-ICNN Value Functions
SOC-ICNNs admit exact dual-variable recovery of first-order geometry and local Hessians as value functions of SOCPs.