Discriminative factorization distinguishes high-quality query sets for black-box model classification, with chance-level error decaying exponentially in query budget and parameters predicting empirical decay rates on auditing tasks.
SVCCA: Singu- lar vector canonical correlation analysis for deep learning dynamics and interpretability
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Black-box model classification under the discriminative factorization
Discriminative factorization distinguishes high-quality query sets for black-box model classification, with chance-level error decaying exponentially in query budget and parameters predicting empirical decay rates on auditing tasks.