A hypergradient-free social-gradient flow is proven to be a descent direction for the planner's objective and converges to the unique socially optimal incentive when social cost depends on agents' joint actions.
MPEC Methods for Bilevel Optimization Problems,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.OC 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Incentive Design without Hypergradients: A Social-Gradient Method
A hypergradient-free social-gradient flow is proven to be a descent direction for the planner's objective and converges to the unique socially optimal incentive when social cost depends on agents' joint actions.