Shared References

← Back to browse

Tag: scalability (1 references)

TRAK: Attributing Model Behavior at Scale 2023 inproceedings

Sung Min Park, Kristian Georgiev, Andrew Ilyas, Guillaume Leclerc, Aleksander Madry

Introduces TRAK (Tracing with the Randomly-projected After Kernel), a data attribution method that is both effective and computationally tractable for large-scale models by leveraging random projections.

data-attributionscalabilityrandom-projectionneural-tangent-kernel
View details Source International Conference on Machine Learning (ICML)