Timezone: »
Poster
DeltaGrad: Rapid retraining of machine learning models
Yinjun Wu · Edgar Dobriban · Susan B Davidson
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.
Author Information
Yinjun Wu (university of pennsylvania)
Edgar Dobriban (University of Pennsylvania)
Susan B Davidson (University of Pennsylvania)
More from the Same Authors
-
2023 : Do Machine Learning Models Learn Statistical Rules Inferred from Data? »
Aaditya Naik · Yinjun Wu · Mayur Naik · Eric Wong -
2023 Poster: Do Machine Learning Models Learn Statistical Rules Inferred from Data? »
Aaditya Naik · Yinjun Wu · Mayur Naik · Eric Wong -
2023 Poster: Demystifying Disagreement-on-the-Line in High Dimensions »
Donghwan Lee · Behrad Moniri · Xinmeng Huang · Edgar Dobriban · Hamed Hassani -
2022 Poster: Unified Fourier-based Kernel and Nonlinearity Design for Equivariant Networks on Homogeneous Spaces »
Yinshuang Xu · Jiahui Lei · Edgar Dobriban · Kostas Daniilidis -
2022 Spotlight: Unified Fourier-based Kernel and Nonlinearity Design for Equivariant Networks on Homogeneous Spaces »
Yinshuang Xu · Jiahui Lei · Edgar Dobriban · Kostas Daniilidis -
2020 Poster: The Implicit Regularization of Stochastic Gradient Flow for Least Squares »
Alnur Ali · Edgar Dobriban · Ryan Tibshirani -
2020 Poster: One-shot Distributed Ridge Regression in High Dimensions »
Yue Sheng · Edgar Dobriban