Preprint
Jun 2026
Global $o(1/k^2)$ Merit Complexity of Regularized Newton Methods for Convex Multiobjective Optimization
An explicit one-dimensional convex bi-objective family is constructed showing that no uniform merit estimate of order $\mathcal O(k^{-(2+\delta)})$ can hold for any fixed $\delta>0$.
Yuqia Wu, Yue Wang, Yaohua Hu
· 0 citations