Datamodels: Predicting Predictions from Training Data

2022 inproceedings ilyas2022datamodels ○ Not yet verified

Authors

Andrew Ilyas, Sung Min Park, Logan Engstrom, Guillaume Leclerc, Aleksander Madry

Venue

International Conference on Machine Learning (ICML)

Abstract

Proposes datamodels that predict model outputs as a function of training data subsets, providing a framework for understanding data attribution through retraining experiments.

BibTeX

Local Entry

@inproceedings{ilyas2022datamodels,
  title = {Datamodels: Predicting Predictions from Training Data},
  author = {Andrew Ilyas and Sung Min Park and Logan Engstrom and Guillaume Leclerc and Aleksander Madry},
  year = {2022},
  booktitle = {International Conference on Machine Learning (ICML)},
  url = {https://arxiv.org/abs/2202.00622},
  abstract = {Proposes datamodels that predict model outputs as a function of training data subsets, providing a framework for understanding data attribution through retraining experiments.}
}

From OPENALEX

@inproceedings{ilyas2022datamodels,
  title = {Datamodels: Predicting Predictions from Training Data},
  author = {Andrew Ilyas and Sung Min Park and Logan Engstrom and Guillaume Leclerc and Aleksander Ma̧dry},
  year = {2022},
  booktitle = {arXiv (Cornell University)},
  doi = {10.48550/arxiv.2202.00622}
}