Mathematical frameworks for non-smooth and nonconvex systems under uncertainty: applications in optimization, control, and game-theoretic equilibria
Keywords:
non-smooth analysis, stochastic approximation, differential inclusions, generalized Nash equilibrium, Clarke subdifferential, nonconvex optimization.Abstract
Many optimization, dynamical systems, and game-theoretic models of interest in learning, control, and economics involve objectives that are non-smooth, nonconvex, and stochastic. Smooth stochastic approximation theory and non smooth analysis each have tools to study different aspects of this complex terrain, but a unifying formalism applicable to all three categories of problems, under one set of regularity assumptions, has yet to emerge. In this paper, we provide such a formalism by viewing the three problem types as examples of a differential inclusion of stochastic processes defined by expected (Aumann integral) Clarke subgradients. We show existence of stationary points for the class of models satisfying a.s. Clarke regularity and integrable upper subgradient bounds; prove the convergence of a projected stochastic subgradient algorithm to the stationary set at Robbins-Monro rates via differential-inclusion ODE techniques; and extend the argument from Rosen on diagonal strict concavity of potential games to prove existence of generalized equilibria for nonconvex potential games with stochastic disturbances. Three applications to piecewise smooth learning in noisy environments, viability-controlled stochastic switched systems, and selection of equilibria in threshold-toll congestion games demonstrate how the three theorems apply in distinct settings.
Downloads
Downloads
Published
Issue
Section
License
You are free to:
- Share — copy and redistribute the material in any medium or format for any purpose, even commercially.
- Adapt — remix, transform, and build upon the material for any purpose, even commercially.
- The licensor cannot revoke these freedoms as long as you follow the license terms.
Under the following terms:
- Attribution — You must give appropriate credit , provide a link to the license, and indicate if changes were made . You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.
- No additional restrictions — You may not apply legal terms or technological measures that legally restrict others from doing anything the license permits.
Notices:
You do not have to comply with the license for elements of the material in the public domain or where your use is permitted by an applicable exception or limitation .
No warranties are given. The license may not give you all of the permissions necessary for your intended use. For example, other rights such as publicity, privacy, or moral rights may limit how you use the material.

