MadryLab / datamodels-data
Data for "Datamodels: Predicting Predictions with Training Data"
☆95Updated last year
Alternatives and similar repositories for datamodels-data:
Users that are interested in datamodels-data are comparing it to the libraries listed below
- ☆28Updated last year
- ☆28Updated 7 months ago
- ☆54Updated 4 years ago
- A modern look at the relationship between sharpness and generalization [ICML 2023]☆43Updated last year
- ☆44Updated 2 years ago
- MetaShift: A Dataset of Datasets for Evaluating Contextual Distribution Shifts and Training Conflicts (ICLR 2022)☆109Updated 2 years ago
- ☆95Updated 2 years ago
- ☆60Updated 3 years ago
- ☆107Updated last year
- Code for Active Learning at The ImageNet Scale. This repository implements many popular active learning algorithms and allows training wi…☆52Updated 3 years ago
- Code for the paper "The Journey, Not the Destination: How Data Guides Diffusion Models"☆21Updated last year
- Code release for REPAIR: REnormalizing Permuted Activations for Interpolation Repair☆46Updated last year
- A fast, effective data attribution method for neural networks in PyTorch☆192Updated 2 months ago
- ☆62Updated 3 years ago
- ☆34Updated last year
- Code for "Just Train Twice: Improving Group Robustness without Training Group Information"☆70Updated 8 months ago
- Recycling diverse models☆44Updated 2 years ago
- ModelDiff: A Framework for Comparing Learning Algorithms☆55Updated last year
- ☆63Updated 2 years ago
- LISA for ICML 2022☆47Updated last year
- Distilling Model Failures as Directions in Latent Space☆46Updated 2 years ago
- Towards Understanding Sharpness-Aware Minimization [ICML 2022]☆35Updated 2 years ago
- A simple PyTorch implementation of influence functions.☆84Updated 7 months ago
- The Pitfalls of Simplicity Bias in Neural Networks [NeurIPS 2020] (http://arxiv.org/abs/2006.07710v2)☆39Updated last year
- Code for NeurIPS'23 paper "A Bayesian Approach To Analysing Training Data Attribution In Deep Learning"☆15Updated last year
- Influence Analysis and Estimation - Survey, Papers, and Taxonomy☆69Updated 11 months ago
- ☆87Updated last year
- Code for the paper "Data Feedback Loops: Model-driven Amplification of Dataset Biases"☆15Updated 2 years ago