Precomputable Leverage Diagnostic
A diagnostic method that computes leverage matrices using only statistics of the forget set and retain set before running an unlearning algorithm, employed to predict the effectiveness of gradient-based unlearning methods.
Timeline (last 90 days)
A direct application of the framework is to generate precomputable leverage diagnostic metrics for auditing the forget set and identifying which type of gradient-based unlearning is more likely to succeed.
The precomputable leverage diagnostics compute the leverage matrices and related metrics using only statistics of the forget set and the retain set, without depending on the specific unlearning optimization process.
All Facts (2)
A direct application of the framework is to generate precomputable leverage diagnostic metrics for auditing the forget set and identifying which type of gradient-based unlearning is more likely to succeed.
50%UnverifiedThe precomputable leverage diagnostics compute the leverage matrices and related metrics using only statistics of the forget set and the retain set, without depending on the specific unlearning optimization process.
50%