Fast Optimistic Gradient Descent Ascent (OGDA) method in continuous and discrete time

Abstract

In the framework of real Hilbert spaces we study continuous in time dynamics as well as numerical algorithms for the problem of approaching the set of zeros of a single-valued monotone and continuous operator $V$. The starting poin is a second order dynamical system that combines a vanishing damping term with the time derivative of $V$ along the trajectory. Our method exhibits fast convergence rates of order $o \left( \frac{1}{t\beta(t)} \right)$ for $\|V(z(t))\|$, wher $\beta(\cdot)$ is a positive nondecreasing function satisfying a growth condition, and also for the restricted gap function. We also prove the weak convergence of the trajectory to a zero of $V$. Temporal discretizations of the dynamical system generate implicit and explicit numerical algorithms, which can be both seen as accelerated versions of the Optimistic Gradient Descent Ascent (OGDA) method, for which we prove that the generated sequence of iterates shares the asymptotic features of the continuous dynamics. In particular we show for the implicit numerical algorithm convergence rates of order $o \left( \frac{1}{k\beta_k} \right)$ for $\|V(z^k)\|$ and the restricted gap function, where $(\beta_k)_{k \geq 0}$ is a positive nondecreasing sequence satisfying a growth condition. For the explicit numerical algorithm we show by additionally assuming that the operator $V$ is Lipschitz continuous convergence rates of order $o \left( \frac{1}{k} \right)$ for $\|V(z^k)\|$ and the restricted gap function. All convergence rate statements are last iterate convergence results; in addition we prove for both algorithms the convergence of the iterates to a zero of $V$. To our knowledge, our study exhibits the best known convergence rate results for monotone equations. Numerical experiments indicate the overwhelming superiority of our explicit numerical algorithm over other methods for monotone equations.