Sign inSign in
ConceptAI & ML

DP-SGD

An algorithm that applies the Gaussian mechanism to gradients when training deep neural networks on sensitive data.
as Kai Chen defines itGoogle Research & TechTalks
Watch it explained

Know first

Named as a prerequisite by the lectures that define this. The number is how many say so. A grey one has no page yet.

Opens up

Concepts that name this one as a prerequisite.

Lecturers

2

Each in their own terms, from the easiest level.

  • Anvith Thudi

    Google Research & TechTalks · Graduate

    Differentially Private Stochastic Gradient Descent, an algorithm that adds noise and clips gradients during training to provide privacy guarantees.
    • 5:18Leveraging Per-Instance Privacy for Machine Unlearning

Lectures that assume it

1

Connections

7

The lectures that define it or assume it, and the concepts next to it.

2 lecturers. Definitions are written by AI from each lecture’s transcript. A time with a play mark starts the lecture at the moment the lecturer says it.