English

A first-order primal-dual method with adaptivity to local smoothness

Optimization and Control 2021-10-29 v1 Machine Learning

Abstract

We consider the problem of finding a saddle point for the convex-concave objective minxmaxyf(x)+Ax,yg(y)\min_x \max_y f(x) + \langle Ax, y\rangle - g^*(y), where ff is a convex function with locally Lipschitz gradient and gg is convex and possibly non-smooth. We propose an adaptive version of the Condat-V\~u algorithm, which alternates between primal gradient steps and dual proximal steps. The method achieves stepsize adaptivity through a simple rule involving A\|A\| and the norm of recently computed gradients of ff. Under standard assumptions, we prove an O(k1)\mathcal{O}(k^{-1}) ergodic convergence rate. Furthermore, when ff is also locally strongly convex and AA has full row rank we show that our method converges with a linear rate. Numerical experiments are provided for illustrating the practical performance of the algorithm.

Keywords

Cite

@article{arxiv.2110.15148,
  title  = {A first-order primal-dual method with adaptivity to local smoothness},
  author = {Maria-Luiza Vladarean and Yura Malitsky and Volkan Cevher},
  journal= {arXiv preprint arXiv:2110.15148},
  year   = {2021}
}
R2 v1 2026-06-24T07:16:01.141Z