In this paper we present a method for the solution of $\ell_1$-regularized convex quadratic optimization problems. It is derived by suitably combining a proximal method of multipliers strategy with a semi-smooth Newton method. The resulting linear systems are solved using a Krylov-subspace method, accelerated by appropriate general-purpose preconditioners, which are shown to be optimal with respect to the proximal parameters. Practical efficiency is further improved by warm-starting the algorithm using a proximal alternating direction method of multipliers. We show that the method achieves global convergence under feasibility assumptions. Furthermore, under additional standard assumptions, the method can achieve global linear and local superlinear convergence. The effectiveness of the approach is numerically demonstrated on $L^1$-regularized PDE-constrained optimization problems.
翻译:在本文中,我们提出了一个解决$@ell_1$-正规化的锥形二次优化问题的方法,它通过适当结合一种接近的乘数战略方法与半悬浮牛顿方法而得出。由此产生的线性系统使用一种Krylov-Sub空间方法来解决,由适当的通用先决条件人加速,这些方法对准度参数来说是最佳的。通过使用一种准氧化交替的乘数方向方法来温暖启动算法,进一步提高了实际效率。我们表明,该方法在可行性假设下实现了全球趋同。此外,根据其他标准假设,该方法可以实现全球线性和本地超线性趋同。该方法的有效性在数字上以1美元正规化的受PDE限制的优化问题为证明。