Three-operator splitting for learning to predict equilibria in convex games

DOI10.1137/22M1544531MaRDI QIDQ6583713zbMATH OpenFDO

Authors Daniel McKenzie, Howard Heaton, Qiuwei Li, Samy Wu Fung, Stanley Osher, Wotao Yin

Publication date 6 August 2024

Published in SIAM Journal on Mathematics of Data Science (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1137/22M1544531

zbMATH Keywords

end-to-end learninggame theorymachine learningoperator splittingvariational inequalities

Mathematics Subject Classification ID

Analysis of algorithms and problem complexity (68Q25) Graph theory (including graph drawing) in computer science (68R10) Computer graphics; computational geometry (digital and algorithmic aspects) (68U05)

Cites work

• A continuous theory of traffic congestion and Wardrop equilibria
• A three-operator splitting scheme and its optimization applications
• Algorithmic Game Theory
• Angenäherte Auflösung von Systemen linearer Gleichungen.
• Calcolo approssimato per le soluzioni dei sistemi di equazioni lineari.
• Convex Analysis
• Convex analysis and monotone operator theory in Hilbert spaces
• Data-driven estimation in equilibrium using inverse optimization
• Equilibrium points in n -person games
• Existence and Uniqueness of Equilibrium Points for Concave N-Person Games
• Existence of an Equilibrium for a Competitive Economy
• scientific article; zbMATH DE number 3128728 (Why is no real title available?)
• Learning correlated equilibria in games with compact sets of strategies
• Learning in games via reinforcement and regularization
• Learning maximally monotone operators for image recovery
• On the convergence of projection methods: Application to the decomposition of affine variational inequalities
• On the effectiveness of projection methods for convex feasibility problems with linear inequality constraints
• On the relationship between Nash—Cournot and Wardrop equilibria
• Projection methods: an annotated bibliography of books and reviews
• Quantal response equilibria for normal form games
• Quelques propriétés des opérateurs angle-bornes et n-cycliquement monotones
• Sensitivity Analysis in Variational Inequalities
• The Baillon-Haddad theorem revisited
• The Little Engine that Could: Regularization by Denoising (RED)
• Wasserstein-based projections with applications to inverse problems

Cited in

(4)

• A hybrid SIAC: data-driven post-processing filter for discontinuities in solutions to numerical PDEs
• Convergence analyses of Davis-Yin splitting via scaled relative graphs
• A symmetric primal-dual method with double extrapolation for composite convex optimization involving three functions
• Truncated Differentiation for Inverse Potential MFGs

This page was built for publication: Three-operator splitting for learning to predict equilibria in convex games

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6583713)