DP-SGD
A machine learning training algorithm that combines differential privacy with stochastic gradient descent. It protects training data privacy by clipping gradients and adding Gaussian noise, and serves as the de facto standard method for training privacy-sensitive models.
Timeline (last 90 days)
DP-SGD is a mechanism for achieving differential privacy in stochastic gradient descent, implemented by clipping per-sample gradients and then adding Gaussian noise.
On a synthetic oncology benchmark, active learning + DP-SGD at ε=3 matched the performance of random sampling + DP-SGD at ε=8 in AUROC.
Differentially private stochastic gradient descent (DP-SGD) has become the de facto standard for training privacy-sensitive models.
The information leaked during training is measured by conditional mutual information (CMI), and for DP-SGD this leakage bound depends only on two hyperparameters: the sampling rate and the noise multiplier.
All Facts (4)
DP-SGD is a mechanism for achieving differential privacy in stochastic gradient descent, implemented by clipping per-sample gradients and then adding Gaussian noise.
50%UnverifiedOn a synthetic oncology benchmark, active learning + DP-SGD at ε=3 matched the performance of random sampling + DP-SGD at ε=8 in AUROC.
50%UnverifiedDifferentially private stochastic gradient descent (DP-SGD) has become the de facto standard for training privacy-sensitive models.
50%UnverifiedThe information leaked during training is measured by conditional mutual information (CMI), and for DP-SGD this leakage bound depends only on two hyperparameters: the sampling rate and the noise multiplier.
50%