Privacy Loss of Noisy Stochastic Gradient Descent Might Converge Even for Non-Convex Losses

Understand

The Noisy-SGD algorithm is widely used for privately training machine learning models.

• Traditional privacy analyses of this algorithm assume that the internal state is publicly revealed, resulting in privacy loss bounds that increase indefinitely with the number of iterations.
• However, recent findings have shown that if the internal state remains hidden, then the privacy loss might remain bounded.
• Nevertheless, this remarkable result heavily relies on the assumption of (strong) convexity of the loss function.