AI Paper Atlas

Research map / Learning theory and algorithms / Prediction and decision losses

Imperfect Influence, Reliable Rankings: A Theory of TRAK for Data Attribution

Han Tong, Shubhangi Ghosh, Haolin Zou, Arian Maleki

NeurIPS 2026 · Learning theory and algorithms › Prediction and decision losses · approach: Data attribution and recourse

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Provides a theoretical analysis of TRAK, a widely used data attribution method that approximates the model with a kernel machine and uses approximate leave-one-out (ALO) techniques.

Problem

Data attribution traces a model's predictions back to training examples; TRAK is empirically strong but its theoretical conditions for reliable attribution rankings were not well understood.

Approach

Theoretical analysis of TRAK as a kernel-machine approximation combined with approximate leave-one-out risk techniques, explaining when its imperfect influence estimates still yield reliable rankings of training data.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add linearization step to true leave-one-out influence (ablation)TRAK · 3-class simulationinfluence accuracy vs trueHurt
add ALO approximation after linearization (ablation)TRAK · 3-class simulationinfluence error: 1.49 -> 1.49No clear effect
reduce random projection dimension from 0.75d to 0.25d (ablation)TRAK · 3-class simulationCorr. 5%/Uncorr. 95% separation: 1.42 -> 0.89Hurt
reduce random projection dimension to 0.1d (ablation)TRAK · 3-class simulationCorr. 5%/Uncorr. 95% separation: 1.42 -> 0.42Hurt
apply linearization and ALO (no projection) (ablation)TRAK · 3-class simulationseparation ratio: 1.66 -> 1.49No clear effect
reduce projection dimension (ablation)TRAK · 3-class simulationcorrelation of TRAK influence with true influenceHurt

Experimental setup

Builds on: TRAK

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy