Generalized mirror descents with non-convex potential functions in atomic congestion games: continuous time and discrete time

DOI10.1016/J.IPL.2017.10.003MaRDI QIDQ1679909zbMATH OpenOpenAlexFDO

Authors Po-An Chen

Publication date 22 November 2017

Published in Information Processing Letters (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/j.ipl.2017.10.003

zbMATH Keywords

convergenceanalysis of algorithmscongestion gamesmirror descentsnonconvex potential function

Mathematics Subject Classification ID

Analysis of algorithms (68W40) Applications of game theory (91A80)

Recommendations

• Generalized mirror descents in congestion games
• Continuous-time convergence rates in potential and monotone games
• Multiplicative updates outperform generic no-regret learning in congestion games (extended abstract)
• Congestion games viewed from M-convexity
• On the convergence of regret minimization dynamics in concave games

Cites work

• Generalized mirror descents in congestion games
• Load balancing without regret in the bulletin board model
• Mirror descent and nonlinear projected subgradient methods for convex optimization.
• Multiplicative updates outperform generic no-regret learning in congestion games (extended abstract)
• On the convergence of regret minimization dynamics in concave games
• Routing without regret, on convergence to Nash equilibria of regret-minimizing algorithms in routing games
• Tatonnement beyond gross substitutes? Gradient descent to the rescue

Cited in

(3)

• Continuous-time convergence rates in potential and monotone games
• Continuous-Time Discounted Mirror Descent Dynamics in Monotone Concave Games
• Generalized mirror descents in congestion games

This page was built for publication: Generalized mirror descents with non-convex potential functions in atomic congestion games: continuous time and discrete time

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1679909)