Adaptive extra-gradient methods for min-max optimization and games
This addresses optimization challenges in games and resource allocation by providing a robust, tuning-free algorithm that handles singularities, though it is incremental in adapting existing methods.
The paper tackles min-max optimization by introducing adaptive extra-gradient methods that automatically adjust to problem geometry, achieving order-optimal convergence rates of O(1/ε) for smooth problems and O(1/ε²) for non-smooth ones without requiring standard boundedness or Lipschitz conditions.
We present a new family of min-max optimization algorithms that automatically exploit the geometry of the gradient data observed at earlier iterations to perform more informative extra-gradient steps in later ones. Thanks to this adaptation mechanism, the proposed method automatically detects whether the problem is smooth or not, without requiring any prior tuning by the optimizer. As a result, the algorithm simultaneously achieves order-optimal convergence rates, i.e., it converges to an $\varepsilon$-optimal solution within $\mathcal{O}(1/\varepsilon)$ iterations in smooth problems, and within $\mathcal{O}(1/\varepsilon^2)$ iterations in non-smooth ones. Importantly, these guarantees do not require any of the standard boundedness or Lipschitz continuity conditions that are typically assumed in the literature; in particular, they apply even to problems with singularities (such as resource allocation problems and the like). This adaptation is achieved through the use of a geometric apparatus based on Finsler metrics and a suitably chosen mirror-prox template that allows us to derive sharp convergence rates for the methods at hand.