An adaptive discretization algorithm for constrained locally optimal experimental design converges to an optimal design when ε=0 and to an ε-optimal design in finitely many steps when ε>0, with reduced computational effort.
Jaggi:Revisiting Frank–Wolfe: projection-free sparse convex optimization.Proceedings of the 30th International Conference on Machine Learning (ICML), PMLR (2013), 427-435
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 adaptive discretization algorithm for locally optimal experimental design with constraints
An adaptive discretization algorithm for constrained locally optimal experimental design converges to an optimal design when ε=0 and to an ε-optimal design in finitely many steps when ε>0, with reduced computational effort.