AI Paper Atlas

Research map / Optimization / Optimizers

Bayesian Influence Functions for Hessian-Free Data Attribution

Philipp Alexander Kreer, Wilson Wu, Maxwell Adam, Zach Furman, Jesse Hoogland

ICLR 2026 · Optimization › Optimizers · approach: Surrogate losses and robust solvers

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
replace Hessian inversion with local posterior covariance (local BIF) instead of EK-FACResNet-9 on CIFAR-10 · CIFAR-10 LDS, small retrain subsetLDSImproved
use local BIF instead of EK-FAC in a language model finetuning settingPythia-14M · Pythia-14M finetuning LDSLDSHurt
use local BIF instead of EK-FAC for small image modelsResNet-9 / CIFAR-10 · compute timeruntime: EK-FAC around five times fasterHurt
use local BIF instead of EK-FAC for large modelsPythia suite · Pythia scaling, evaluation timeevaluation time: 2 orders of magnitude faster at largest sizesImproved
use local BIF instead of EK-FAC for GPU memoryPythia suite · Pythia scaling, peak GPU RAMpeak GPU RAMNo clear effect
decrease attribution set size (ablation)all TDA methods on CIFAR-10 · CIFAR-10 LDSLDSImproved
use RMSprop-SGLD preconditioning (ablation)local BIF sampler · hyperparameter robustnessresult qualityImproved

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