Incentive Design without Hypergradients: A Social-Gradient Method

arXiv:2604.11346 · math.OC, cs.GT, cs.MA, cs.SY, eess.SY · Submitted 2026-04-13 · Read on arXiv

math.OC, cs.GT, cs.MA, cs.SY, eess.SY

Submitted: 2026-04-13

Updated: 2026-09-18

Terminology

• Gradient Flow — 11× in this paper · explained in 2 episodes
• Nash Equilibrium — 9× in this paper · explained in 2 episodes
• Information Asymmetry — 5× in this paper · explained in 2 episodes
• Adaptation — 2× in this paper · explained in 1 episode
• Conference on Decision and Control — 2× in this paper
• Mathematical Program with Equilibrium Constraints — 2× in this paper
• Adjacency Matrix — 1× in this paper · explained in 1 episode
• Lyapunov function — 1× in this paper · explained in 2 episodes

Sources

• Adaptive Incentive Design with Learning Agents

Related papers

• Lions and Muons: Optimization via Stochastic Frank-Wolfe under Heavy-Tailed Noise
• Adam-HNAG: A Convergent Reformulation of Adam with Accelerated Rate
• Incremental Learning in Mirror Flows
• Online Control via Counterfactual Tracking
• Asynchronous Replanning in Two Population Linear Quadratic Mean Field Games: Information Requirements and Stability
• Petrov-Galerkin operator inference with application to stability-encouraging identification