arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2107.08281math.OC
收藏

具有对偶性的复合优化的线性收敛 FISTA 变体

Linearly-Convergent FISTA Variant for Composite Optimization with Duality

Casey Garner, Shuzhong Zhang

AI总结:

提出 FISTA 的新变体 C-FISTA,利用 Fenchel 对偶性证明其在更广泛的复合模型上实现全局线性收敛,并在组 Lasso 和组逻辑回归模型上优于现有求解器。

摘要:

许多大规模优化问题可以表示为复合优化模型。诸如快速迭代收缩阈值算法(FISTA)等加速一阶方法已被证明对许多大型复合模型有效。在本文中,我们提出了 FISTA 的一种新变体,称为 C-FISTA,它比许多最新的 FISTA 变体在更广泛的复合模型类上获得了全局线性收敛。我们通过展示 C-FISTA 在组 Lasso 和组逻辑回归模型上均优于当前的一阶求解器,证明了 C-FISTA 的多功能性和有效性。此外,我们利用 Fenchel 对偶性证明了 C-FISTA 在不损失全局线性收敛的情况下为一大类凸模型提供了全局线性收敛。

英文摘要:

Many large-scale optimization problems can be expressed as composite optimization models. Accelerated first-order methods such as the fast iterative shrinkage-thresholding algorithm (FISTA) have proven effective for numerous large composite models. In this paper, we present a new variation of FISTA, to be called C-FISTA, which obtains global linear convergence for a broader class of composite models than many of the latest FISTA variants. We demonstrate the versatility and effectiveness of C-FISTA by showing C-FISTA outperforms current first-order solvers on both group Lasso and group logistic regression models. Furthermore, we utilize Fenchel duality to prove C-FISTA provides global linear convergence for a large class of convex models without the loss of global linear convergence.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑