Fast FISTA Algorithm With New Backtracking Technique For Multiobjective Optimization
| Autor: | Huang, Chengzhi, Chen, Jian, Tang, Liping |
|---|---|
| Rok vydání: | 2024 |
| Předmět: | |
| Druh dokumentu: | Working Paper |
| Popis: | This paper proposes a new backtracking strategy based on the FISTA accelerated algorithm for multiobjective optimization problems. The strategy addresses the limitation of existing algorithms that struggle to handle situations where the Lipschitz constant $L(f)$ of the objective function's gradient is still being determined. It mitigates the petite iteration step sizes caused by a significant value of $L(f)$. Furthermore, the proposed strategy effectively avoids the limitation in convergence proofs arising from the non-negativity of the auxiliary sequence $W_k(z):= \min_{i =1,\dotsb,m} [F_i(x_k) - F_i(z)]$, thus providing a theoretical guarantee for its performance. We demonstrate that, under relatively mild assumptions, the algorithm achieves the convergence rate of $O(1/k^2)$. Comment: arXiv admin note: text overlap with arXiv:2312.01609 |
| Databáze: | arXiv |
| Externí odkaz: |
|