arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2005.00959math.OCcs.CVcs.LGcs.NAmath.NAstat.ML
收藏

基于反投影的目标投影梯度下降的收敛速度

On the Convergence Rate of Projected Gradient Descent for a Back-Projection based Objective

Tel Aviv University(特拉维夫大学)

Tom Tirer, Raja Giryes

摘要:

不适定线性反问题出现在许多科学系统中,通常通过求解由数据保真度和先验项组成的最优化问题来解决。最近,一些作品已经考虑了反投影(BP)为基础的保真度项作为一种替代常见的最小二乘(LS),并表现出良好的效果流行的反问题。这些工作还经验性地表明,使用BP项而不是LS项,需要更少的优化算法迭代。在本文中,我们研究的收敛速度的投影梯度下降(PGD)算法的BP目标。我们的分析可以确定其更快的收敛速度相比,使用LS目标的内在来源,同时只做温和的假设。我们还分析了更一般的近端梯度法在松弛收缩条件下对先验的近端映射的影响。该分析进一步突出了BP算法在线性测量算子条件不好时的优势。用$\ell_1$ -范数和基于GAN的先验进行的数值实验证实了我们的理论结果。

英文摘要:

Ill-posed linear inverse problems appear in many scientific setups, and are typically addressed by solving optimization problems, which are composed of data fidelity and prior terms. Recently, several works have considered a back-projection (BP) based fidelity term as an alternative to the common least squares (LS), and demonstrated excellent results for popular inverse problems. These works have also empirically shown that using the BP term, rather than the LS term, requires fewer iterations of optimization algorithms. In this paper, we examine the convergence rate of the projected gradient descent (PGD) algorithm for the BP objective. Our analysis allows to identify an inherent source for its faster convergence compared to using the LS objective, while making only mild assumptions. We also analyze the more general proximal gradient method under a relaxed contraction condition on the proximal mapping of the prior. This analysis further highlights the advantage of BP when the linear measurement operator is badly conditioned. Numerical experiments with both $\ell_1$-norm and GAN-based priors corroborate our theoretical results.

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。

↑