Generalized Front Descent algorithms for unconstrained multi-objective optimization achieve set-wise stationarity convergence with iteration complexity bounds and outperform prior methods empirically.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.OC 1years
2024 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Effective Front-Descent Algorithms with Convergence Guarantees
Generalized Front Descent algorithms for unconstrained multi-objective optimization achieve set-wise stationarity convergence with iteration complexity bounds and outperform prior methods empirically.