The paper frames learning as an optimal control problem and claims an iff characterization of optimal learning trajectories via the maximum principle, plus a Galerkin successive approximation algorithm.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.OC 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
On characterizing optimal learning trajectories in a class of learning problems
The paper frames learning as an optimal control problem and claims an iff characterization of optimal learning trajectories via the maximum principle, plus a Galerkin successive approximation algorithm.