18 citations · 36 across the 9 of their papers we have counts for
Showing stat.MLShow all
2 papers · 1 filter
stat.ML2023★ 10 cited
TRAK: Attributing Model Behavior at Scale
Sung Min Park, Kristian Georgiev, Andrew Ilyas +2
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 for…
stat.ML2022★ 18 cited
Datamodels: Predicting Predictions from Training Data
Andrew Ilyas, Sung Min Park, Logan Engstrom +2
We present a conceptual framework, datamodeling, for analyzing the behavior of a model class in terms of the training data. For any fixed "target" example , training set , an…