The decision problem for the optimal objective value (and unboundedness) of a k-level linear program is Σ^p_{k-1}-complete.
Yijiang River Dong, Hongzhou Lin, Mikhail Belkin, Ramon Huerta, and Ivan Vulic
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
representative citing papers
A penalty-based bi-level optimization framework for machine unlearning that decorrelates forget and retention gradients via inner maximization and restores utility via outer minimization, with convergence guarantees and improved trade-offs on vision and language benchmarks.
citing papers explorer
-
Decision Problems in Multilevel Linear Programming
The decision problem for the optimal objective value (and unboundedness) of a k-level linear program is Σ^p_{k-1}-complete.
-
OFMU: Optimization-Driven Framework for Machine Unlearning
A penalty-based bi-level optimization framework for machine unlearning that decorrelates forget and retention gradients via inner maximization and restores utility via outer minimization, with convergence guarantees and improved trade-offs on vision and language benchmarks.