Regularized A-optimal design is NP-hard, and a new convex relaxation dominates previous ones with finite optimality gaps for every k, enabling faster exact and greedy solvers.
International conference on machine learning, 498--507 (PMLR)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.OC 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Strong Formulations and Algorithms for Regularized A-optimal Design
Regularized A-optimal design is NP-hard, and a new convex relaxation dominates previous ones with finite optimality gaps for every k, enabling faster exact and greedy solvers.