DeltaGrad: Rapid retraining of machine learning models
arXiv:2006.14755
Abstract
Machine learning models are not static and may need to be retrained on slightly changed datasets, for instance, with the addition or deletion of a set of data points. This has many applications, including privacy, robustness, bias reduction, and uncertainty quantifcation. However, it is expensive to retrain models from scratch. To address this problem, we propose the DeltaGrad algorithm for rapid retraining machine learning models based on information cached during the training phase. We provide both theoretical and empirical support for the effectiveness of DeltaGrad, and show that it compares favorably to the state of the art.
Cited by in corpus (8)
- Fast Yet Effective Machine Unlearning
- Zero-Shot Machine Unlearning
- On the Necessity of Auditable Algorithmic Definitions for Machine Unlearning
- DeepObliviate: A Powerful Charm for Erasing Data Residual Memory in Deep Neural Networks
- Outage-Watch: Early Prediction of Outages using Extreme Event Regularizer
- SSSE: Efficiently Erasing Samples from Trained Machine Learning Models
- ModelPred: A Framework for Predicting Trained Model from Training Data
- Minimax Optimization: The Case of Convex-Submodular