Sifting through the noise: Universal first-order methods for stochastic variational inequalities - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2021

Sifting through the noise: Universal first-order methods for stochastic variational inequalities

Résumé

We examine a flexible algorithmic framework for solving monotone variational inequalities in the presence of randomness and uncertainty. The proposed template encompasses a wide range of popular first-order methods, including dual averaging, dual extrapolation and optimistic gradient algorithms – both adaptive and non-adaptive. Our first result is that the algorithm achieves the optimal rates of convergence for cocoercive problems when the profile of the randomness is known to the optimizer: $\mathcal{O}(1/\sqrt{T})$ for absolute noise profiles, and $\mathcal{O}(1/T)$ for relative ones. Subsequently, we drop all prior knowledge requirements (the absolute/relative variance of the randomness affecting the problem, the operator's cocoercivity constant, etc.), and we analyze an adaptive instance of the method that gracefully interpolates between the above rates – i.e. it achieves $\mathcal{O}(1/\sqrt{T})$ and $\mathcal{O}(1/T)$ in the absolute and relative cases, respectively. To our knowledge, this is the first universality result of its kind in the literature and, somewhat surprisingly, it shows that an extra-gradient proxy step is not required to achieve optimal rates.
Fichier principal
Vignette du fichier
RelativeNoise.pdf (8.02 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03357714 , version 1 (29-09-2021)

Identifiants

  • HAL Id : hal-03357714 , version 1

Citer

Kimon Antonakopoulos, Thomas Pethick, Ali Kavis, Panayotis Mertikopoulos, Volkan Cevher. Sifting through the noise: Universal first-order methods for stochastic variational inequalities. NeurIPS 2021 - 35th International Conference on Neural Information Processing Systems, Dec 2021, Virtual, Unknown Region. pp.1-39. ⟨hal-03357714⟩
156 Consultations
92 Téléchargements

Partager

Gmail Facebook X LinkedIn More