A distributed bilevel algorithm optimizes emergent macroscopic behavior in multi-agent systems by combining local exponential-family state estimation with hypergradient microscopic updates and proves convergence via timescale separation.
A survey of distributed optimization
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
-
A Distributed Bilevel Framework for the Macroscopic Optimization of Multi-Agent Systems
A distributed bilevel algorithm optimizes emergent macroscopic behavior in multi-agent systems by combining local exponential-family state estimation with hypergradient microscopic updates and proves convergence via timescale separation.