Timezone: »

Semi Bandit dynamics in Congestion Games: Convergence to Nash Equilibrium and No-Regret Guarantees.
Ioannis Panageas · EFSTRATIOS PANTELEIMON SKOULAKIS · Luca Viano · Xiao Wang · Volkan Cevher

Tue Jul 25 05:00 PM -- 06:30 PM (PDT) @ Exhibit Hall 1 #411

In this work, we propose introduce a variant of online stochastic gradient descent and prove it converges to Nash equilibria and simultaneously it has sublinear regret for the class of congestion games in the semi-bandit feedback setting. Our proposed method admits convergence rates depending only polynomially on the number of players and the number of facilities, but not on the size of the action set, which can be exponentially large in terms of the number of facilities. Moreover, the running time of our method has polynomial-time dependence on the implicit description of the game. Our analysis exploits techniques from convex geometry, in particular Caratheodory's theorem and recent advances in non-convex stochastic optimization. This work improves upon and answers an open question from (Cui et al 2022).

Author Information

Ioannis Panageas (UC Irvine)
Luca Viano (EPFL)
Xiao Wang (Shanghai University of Finance and Economics)
Volkan Cevher (EPFL)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors