The convergence rate of the accelerated proximal gradient algorithm for Multiobjective Optimization is faster than $O(1/k^2)$

Abstract

In this paper, we propose a fast proximal gradient algorithm for multiobjective optimization, it is proved that the convergence rate of the accelerated algorithm for multiobjective optimization developed by Tanabe et al. can be improved from $O(1/k^2)$ to $o(1/k^2)$ by introducing different extrapolation term $\frac{k-1}{k+\alpha -1}$ with $\alpha >3$. Further, we establish the inexact version of the proposed algorithm when the error term is additive, which owns the same convergence rate. At last, the efficiency of the proposed algorithm is verified on some numerical experiments.