The goal of predictive data attribution is to estimate how adding or removing a given set of training datapoints will affect model predictions. In convex settings, this goal is straightforward (i.e., via the infinitesimal jackknife). In large-scale (non-convex) settings, however, existing methods are far less successful -- current methods' estimates often only weakly correlate with ground truth. In this work, we present a new data attribution method (MAGIC) that combines classical methods and recent advances in metadifferentiation to (nearly) optimally estimate the effect of adding or removing training data on model predictions.
@article{arxiv.2504.16430,
title = {MAGIC: Near-Optimal Data Attribution for Deep Learning},
author = {Andrew Ilyas and Logan Engstrom},
journal= {arXiv preprint arXiv:2504.16430},
year = {2025}
}