Image de couverture de livre

Rescaled Influence Functions: Accurate Data Attribution in High Dimension

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Rubinstein, Ittai, Hopkins, Samuel B.
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

On the Accuracy of Newton Step and Influence Function Data Attributions
par: Rubinstein, Ittai, et autres
Publié: (2025)

Robustness Auditing for Linear Regression: To Singularity and Beyond
par: Rubinstein, Ittai, et autres
Publié: (2024)

Revisiting Data Attribution for Influence Functions
par: Zhu, Hongbo, et autres
Publié: (2025)

Bayesian Influence Functions for Hessian-Free Data Attribution
par: Kreer, Philipp Alexander, et autres
Publié: (2025)

The Quasi-probability Method and Applications for Trace Reconstruction
par: Rubinstein, Ittai
Publié: (2024)

An Iterative Algorithm for Rescaled Hyperbolic Functions Regression
par: Gao, Yeqi, et autres
Publié: (2023)

Influence Functions for Scalable Data Attribution in Diffusion Models
par: Mlodozeniec, Bruno, et autres
Publié: (2024)

A Versatile Influence Function for Data Attribution with Non-Decomposable Loss
par: Deng, Junwei, et autres
Publié: (2024)

High-Layer Attention Pruning with Rescaling
par: Liu, Songtao, et autres
Publié: (2025)

LoRIF: Low-Rank Influence Functions for Scalable Training Data Attribution
par: Li, Shuangqi, et autres
Publié: (2026)

Influence Dynamics and Stagewise Data Attribution
par: Lee, Jin Hwa, et autres
Publié: (2025)

Distributional Training Data Attribution: What do Influence Functions Sample?
par: Mlodozeniec, Bruno, et autres
Publié: (2025)

Which Data Attributes Stimulate Math and Code Reasoning? An Investigation via Influence Functions
par: Kou, Siqi, et autres
Publié: (2025)

Interaction-Aware Influence Functions for Group Attribution
par: Heo, Jaeseung, et autres
Publié: (2026)

Integrated Influence: Data Attribution with Baseline
par: Yang, Linxiao, et autres
Publié: (2025)

SeeDNorm: Self-Rescaled Dynamic Normalization
par: Cai, Wenrui, et autres
Publié: (2025)

Accumulative SGD Influence Estimation for Data Attribution
par: Shi, Yunxiao, et autres
Publié: (2025)

Adaptive Data Analysis for Growing Data
par: Marchant, Neil G., et autres
Publié: (2024)

Fast, Sample-Efficient, Affine-Invariant Private Mean and Covariance Estimation for Subgaussian Distributions
par: Brown, Gavin, et autres
Publié: (2023)

Hypothesis Class Determines Explanation: Why Accurate Models Disagree on Feature Attribution
par: B, Thackshanaramana
Publié: (2026)

Imperfect Influence, Preserved Rankings: A Theory of TRAK for Data Attribution
par: Tong, Han, et autres
Publié: (2026)

Data Attribution for Diffusion Models: Timestep-induced Bias in Influence Estimation
par: Xie, Tong, et autres
Publié: (2024)

Temporal Score Rescaling for Temperature Sampling in Diffusion and Flow Models
par: Xu, Yanbo, et autres
Publié: (2025)

Support Vector Machine Classifier with Rescaled Huberized Pinball Loss
par: Diao, Shibo
Publié: (2025)

Non-Vacuous Generalization Bounds: Can Rescaling Invariances Help?
par: Rouchouse, Damien, et autres
Publié: (2025)

Recovering Plasticity of Neural Networks via Soft Weight Rescaling
par: Oh, Seungwon, et autres
Publié: (2025)

AMLA: MUL by ADD in FlashAttention Rescaling
par: Liao, Qichen, et autres
Publié: (2025)

Self-Attribution Bias: When AI Monitors Go Easy on Themselves
par: Khullar, Dipika, et autres
Publié: (2026)

A Snapshot of Influence: A Local Data Attribution Framework for Online Reinforcement Learning
par: Hu, Yuzheng, et autres
Publié: (2025)

Energy-Based Model for Accurate Estimation of Shapley Values in Feature Attribution
par: Lu, Cheng, et autres
Publié: (2024)

Adversarially-Robust Inference on Trees via Belief Propagation
par: Hopkins, Samuel B., et autres
Publié: (2024)

Diffusion Attribution Score: Evaluating Training Data Influence in Diffusion Models
par: Lin, Jinxu, et autres
Publié: (2024)

Fast Fourier Correlation is a Highly Efficient and Accurate Feature Attribution Algorithm from the Perspective of Control Theory and Game Theory
par: Liu, Zechen, et autres
Publié: (2025)

STAR: Spectral Truncation and Rescale for Model Merging
par: Lee, Yu-Ang, et autres
Publié: (2025)

Attribute Graphs Underlying Molecular Generative Models: Path to Learning with Limited Data
par: Hoffman, Samuel C., et autres
Publié: (2022)

Concept Influence: Leveraging Interpretability to Improve Performance and Efficiency in Training Data Attribution
par: Kowal, Matthew, et autres
Publié: (2026)

Variance Control via Weight Rescaling in LLM Pre-training
par: Owen, Louis, et autres
Publié: (2025)

Influence-based Attributions can be Manipulated
par: Yadav, Chhavi, et autres
Publié: (2024)

General Loss Functions Lead to (Approximate) Interpolation in High Dimensions
par: Lai, Kuo-Wei, et autres
Publié: (2023)

Measuring Stochastic Data Complexity with Boltzmann Influence Functions
par: Ng, Nathan, et autres
Publié: (2024)