A derivative-free projection algorithm with randomized neural networks solves high-dimensional stochastic optimal control and mean field control problems by regressing controls instead of minimizing loss via backpropagation.
Zhang.Backward Stochastic Differential Equations: From Linear to Fully Nonlinear Theory, volume 86 ofProbability Theory and Stochastic Modelling
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
-
An Effective Particle Gradient Projection Method for Solving Stochastic and Mean Field Control Problem
A derivative-free projection algorithm with randomized neural networks solves high-dimensional stochastic optimal control and mean field control problems by regressing controls instead of minimizing loss via backpropagation.