3 papers
cs.LG2026
On the Accuracy of Newton Step and Influence Function Data Attributions
Ittai Rubinstein, Samuel B. Hopkins
Data attribution aims to explain model predictions by estimating how they would change if certain training points were removed, and is used in a wide range of applications, from in…
cs.LG2025
Rescaled Influence Functions: Accurate Data Attribution in High Dimension
Ittai Rubinstein, Samuel B. Hopkins
How does the training data affect a model's behavior? This is the question we seek to answer with data attribution. The leading practical approaches to data attribution are based o…
cs.LG2024
Robustness Auditing for Linear Regression: To Singularity and Beyond
Ittai Rubinstein, Samuel B. Hopkins
It has recently been discovered that the conclusions of many highly influential econometrics studies can be overturned by removing a very small fraction of their samples (often les…