A stable rank network with a known Lipschitz constant certifies robustness radii for persistence diagrams, and on ORBIT5K it keeps high robust accuracy where a standard PersLay model collapses.
In order to test the robustness of Perslay in PyTorch we reimplement it with the following DeepSet (Zaheer et al.,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Certifying Robustness via Topological Representations
A stable rank network with a known Lipschitz constant certifies robustness radii for persistence diagrams, and on ORBIT5K it keeps high robust accuracy where a standard PersLay model collapses.