Improving Differentially Private SGD via Randomly Sparsified Gradients

Differentially private stochastic gradient descent (DP-SGD) has been widely adopted in deep learning to provide rigorously defined privacy, which requires gradient clipping to bound the maximum norm of individual gradients and additive isotropic Gaussian noise. With analysis of the convergence rate of DP-SGD in a non-convex setting, we reveal that randomly sparsifying gradients before clipping and noisification adjusts a trade-off between internal components of the convergence bound and leads to a smaller upper bound when the noise is dominant. Additionally, our theoretical analysis and extensive empirical evaluations show that the trade-off is not trivial but possibly a unique property of DP-SGD, as either canceling noisification or gradient clipping removes the trade-off in the bound. Based on the analysis, we propose an efficient and lightweight approach of random sparsification (RS) for DP-SGD. Applying RS across various DP-SGD frameworks improves performance, while the produced sparse gradients of RS exhibit advantages in reducing communication cost and strengthening security against reconstruction attacks, which are also key problems in private machine learning