Distributional Training Data Attribution: What do Influence Functions Sample?

NeurIPSSpotlight2025

Authors: Bruno Kacper Mlodozeniec, Isaac Reid, Samuel Power, David Krueger, Murat A Erdogdu, Richard E. Turner, Roger Baker Grosse
Venue: NeurIPS 2025
Track: Spotlight

TL;DR

Randomness is an unavoidable part of training deep learning models, yet something that traditional training data attribution algorithms fail to rigorously account for…

Opening excerpt from the authors’ abstract. source

Read the paper

OpenReview

← All NeurIPS 2025 Spotlight papers · Browse the whole archive