Uncertainty quantification by block bootstrap for differentially private stochastic gradient descent.
Holger DetteCarina GrawPublished in: CoRR (2024)
Keyphrases
- differentially private
- stochastic gradient descent
- least squares
- loss function
- differential privacy
- matrix factorization
- contingency tables
- step size
- random forests
- weight vector
- regularization parameter
- multiple kernel learning
- online algorithms
- collaborative filtering
- cross validation
- data sets
- importance sampling
- support vector machine
- ensemble methods
- active learning
- support vector