arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2010.09545math.OCstat.ML
收藏

用展开算法学习求解TV正则化问题

Learning to solve TV regularized problems with unrolled algorithms

Hamza Cherkaoui, Jeremias Sulam, Thomas Moreau

摘要:

全变差(TV)是一种流行的正则化策略,其通过约束估计信号的一阶导数的$\ell_1$范数来促进分段恒定信号。所得到的最优化问题通常使用迭代算法来解决,例如近似梯度下降、原始对偶法或ADMM。然而,这样的方法可能需要非常大量的迭代来收敛到合适的解。在本文中,我们加速这样的迭代算法展开近端梯度下降求解器,以学习他们的参数为1D电视正则化问题。虽然这可以使用合成配方,我们证明,这会导致较慢的性能。在分析公式中应用这种方法的主要困难在于提出一种通过邻近算子计算导数的方法。作为我们的主要贡献,我们开发和表征两种方法来做到这一点,描述他们的好处和局限性,并讨论他们实际上可以改善迭代程序的制度。我们验证了这些研究结果与合成和真实数据的实验。

英文摘要:

Total Variation (TV) is a popular regularization strategy that promotes piece-wise constant signals by constraining the $\ell_1$-norm of the first order derivative of the estimated signal. The resulting optimization problem is usually solved using iterative algorithms such as proximal gradient descent, primal-dual algorithms or ADMM. However, such methods can require a very large number of iterations to converge to a suitable solution. In this paper, we accelerate such iterative algorithms by unfolding proximal gradient descent solvers in order to learn their parameters for 1D TV regularized problems. While this could be done using the synthesis formulation, we demonstrate that this leads to slower performances. The main difficulty in applying such methods in the analysis formulation lies in proposing a way to compute the derivatives through the proximal operator. As our main contribution, we develop and characterize two approaches to do so, describe their benefits and limitations, and discuss the regime where they can actually improve over iterative procedures. We validate those findings with experiments on synthetic and real data.

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。

↑