Mathematical frameworks for non-smooth and nonconvex systems under uncertainty: applications in optimization, control, and game-theoretic equilibria

Authors

  • Saniya Khurana Author
  • Tanveer Ahmad Wani Author
  • D. Balaji Author
  • Kaustubh Milind Utpat Author
  • Vundela Swathi Author
  • Arsh Goyal Author
  • Dr. Chetansinh R. Vaghela Author

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

Download data is not yet available.

Downloads

Published

2026-09-22

How to Cite

Mathematical frameworks for non-smooth and nonconvex systems under uncertainty: applications in optimization, control, and game-theoretic equilibria. (2026). Minimax Theory and Its Applications, 11(2s), 508-516. https://journalmta.com/index.php/jmta/article/view/432