Data Science Wire

Data Attribution at Scale via Influence Matrix Estimation

arXiv stat.ML22h4 min read

arXiv:2609.15044v1 Announce Type: new Abstract: Data attribution seeks to quantify how individual training examples shape a model's predictions and underpins problems including data valuation, machine unlearning, and model interpretability. Despite having a long line of work, computationally scalable methods often struggle to predict the effect of removing training data in neural networks due to their non-convex nature. To overcome this challenge, metagradient-based methods such as MAGIC (Ilyas and Engstrom, 2025) differentiate each prediction through the entire training run and compute its ex

Read the full story at arXiv stat.ML

More in Machine Learning