Imitation learning yields provably stable feedback policies for partially observed Vlasov-Poisson instabilities, with error floors determined by minimal behavior-cloning loss characterized via entropy of the initial distribution.
Control of instability in a Vlasov-Poisson system through an external electric field
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Provable imitation learning for control of instability in partially-observed Vlasov--Poisson equations
Imitation learning yields provably stable feedback policies for partially observed Vlasov-Poisson instabilities, with error floors determined by minimal behavior-cloning loss characterized via entropy of the initial distribution.