A loop-transformation convexification plus a randomized subspace sketch for Lipschitz-constrained training; the sketch's high-probability certificate is not mathematically justified.
Globally-robust neural net- works,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
A Scalable Approach for Safe and Robust Learning via Lipschitz-Constrained Networks
A loop-transformation convexification plus a randomized subspace sketch for Lipschitz-constrained training; the sketch's high-probability certificate is not mathematically justified.