Differentially Private Algorithms for the Stochastic Saddle Point Problem with Optimal Rates for the Strong Gap

We show that convex-concave Lipschitz stochastic saddle point problems (also known as stochastic minimax optimization) can be solved under the constraint of (ε,δ)-differential privacy with strong (primal-dual) gap rate of tilde Obig(frac1√n + frac√dnεbig), where n is the dataset size and d is the dimension of the problem. This rate is nearly optimal, based on existing lower bounds in differentially private stochastic optimization. Specifically, we prove a tight upper bound on the strong gap via novel implementation and analysis of the recursive regularization technique repurposed for saddle point problems. We show that this rate can be attained with Obig(minbigfracn2ε1.5√d, n3/2bigbig) gradient complexity, and tildeO(n) gradient complexity if the loss function is smooth. As a byproduct of our method, we develop a general algorithm that, given a black-box access to a subroutine satisfying a certain α primal-dual accuracy guarantee with respect to the empirical objective, gives a solution to the stochastic saddle point problem with a strong gap of tildeO(α+frac1√n). We show that this α-accuracy condition is satisfied by standard algorithms for the empirical saddle point problem such as the proximal point method and the stochastic gradient descent ascent algorithm. Further, we show that even for simple problems it is possible for an algorithm to have zero weak gap and suffer from Omega(1) strong gap. We also show that there exists a fundamental tradeoff between stability and accuracy. Specifically, we show that any Delta-stable algorithm has empirical gap Omegabig(frac1Delta nbig), and that this bound is tight. This result also holds also more specifically for empirical risk minimization problems and may be of independent interest.