English

Second-Order Mirror Descent: Convergence in Games Beyond Averaging and Discounting

Optimization and Control 2024-10-28 v4 Computer Science and Game Theory Machine Learning Systems and Control Systems and Control Dynamical Systems

Abstract

In this paper, we propose a second-order extension of the continuous-time game-theoretic mirror descent (MD) dynamics, referred to as MD2, which provably converges to mere (but not necessarily strict) variationally stable states (VSS) without using common auxiliary techniques such as time-averaging or discounting. We show that MD2 enjoys no-regret as well as an exponential rate of convergence towards strong VSS upon a slight modification. MD2 can also be used to derive many novel continuous-time primal-space dynamics. We then use stochastic approximation techniques to provide a convergence guarantee of discrete-time MD2 with noisy observations towards interior mere VSS. Selected simulations are provided to illustrate our results.

Keywords

Cite

@article{arxiv.2111.09982,
  title  = {Second-Order Mirror Descent: Convergence in Games Beyond Averaging and Discounting},
  author = {Bolin Gao and Lacra Pavel},
  journal= {arXiv preprint arXiv:2111.09982},
  year   = {2024}
}

Comments

16 pages, 12 figures. This work has been submitted to the IEEE for possible publication