Data Attribution: From Classifiers to Generative Models
The goal of data attribution is to trace model predictions back to training data. Despite a long line of work towards this goal, existing approaches to data attribution tend to force users to choose between computational tractability and efficacy. That is, computationally tractable methods can strug...
Main Author: | Georgiev, Kristian |
---|---|
Other Authors: | Mądry, Aleksander |
Format: | Thesis |
Published: |
Massachusetts Institute of Technology
2023
|
Online Access: | https://hdl.handle.net/1721.1/152676 |
Similar Items
-
Learning classifiers from medical data
by: Billing, Jeffrey J. (Jeffrey Joel), 1979-
Published: (2005) -
Reusing an ontology to generate numeral classifiers
by: Bond, Francis., et al.
Published: (2011) -
Visual Charting of Classified Audio Data
by: Archer, William
Published: (2023) -
Learning to classify from impure samples with high-dimensional data
by: Nachman, Benjamin, et al.
Published: (2018) -
A multilevel cross-classified modelling approach to peer review of grant proposals: the effects of assessor and researcher attributes on assessor ratings
by: Jayasinghe, U, et al.
Published: (2003)