Rescaled influence functions, which account for the change in the Hessian when a sample is removed, dramatically improve leave-T-out effect estimates compared to standard influence functions in high-dimensional logistic regression, with negligible computational overhead.
Title resolution pending
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
-
Rescaled Influence Functions: Accurate Data Attribution in High Dimension
Rescaled influence functions, which account for the change in the Hessian when a sample is removed, dramatically improve leave-T-out effect estimates compared to standard influence functions in high-dimensional logistic regression, with negligible computational overhead.