Unverified50% confidenceFactExact time
These two leverage matrices are shown both theoretically and experimentally to drive the influence of the unlearning residual on forget outputs and retain outputs.
1
Sources
50%
Confidence
Long-term
Relevance
10/30/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe two core metrics for measuring machine unlearning quality are Forget Rate and Retain Rate; these two metrics are in natural tension, as excessive forgetting can lead to concept collapse.77% similarUnverifiedExisting gradient-based unlearning methods account only partially for the geometric relationships characterized by the leverage matrices, causing them to deviate significantly from the retrained model in output-space behavior.77% similarUnverifiedThis study reveals a fundamental disconnect between loss and behavior in gradient-based machine unlearning and provides a unified output-space analysis framework.75% similarUnverifiedPreconditioning can accelerate iterative convergence, but preconditioner matrices often require substantial memory, which constitutes a trade-off between convergence speed and memory.71% similarUnverifiedIn practice, precision and recall are commonly used to quantify false positives and false negatives, and confusion matrices are used to analyze model performance.70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1113845API
curl https://kongchang.com/api/v1/knowledge/claims/1113845MCP
get_claim(id=1113845)