AI engineering glossary · AI ethics law product
What is DP-SGD?
DP-SGD (also called differentially private stochastic gradient descent): A training algorithm that makes a neural network differentially private by clipping each example's gradient to a maximum size and adding random noise before every update. It limits how much any single training record can influence the model, at some cost in accuracy.
DP-SGD: an example
A hospital trains a diagnosis model with clipped, noised gradients so that the model cannot memorise any one patient's record.
Related terms
More AI ethics law product terms
- DPDP Act 2023
- DPDP Rules 2025
- Edit rate
- Equal opportunity
- Equalized odds
- Escalation rate
- EU AI Act
- Explainable AI
Where you learn it
DP-SGD is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.