当前位置: X-MOL 学术SIAM J. Optim. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Accelerated Iterative Regularization via Dual Diagonal Descent
SIAM Journal on Optimization ( IF 2.6 ) Pub Date : 2021-03-01 , DOI: 10.1137/19m1308888
Luca Calatroni , Guillaume Garrigos , Lorenzo Rosasco , Silvia Villa

SIAM Journal on Optimization, Volume 31, Issue 1, Page 754-784, January 2021.
We propose and analyze an accelerated iterative dual diagonal descent algorithm for the solution of linear inverse problems with strongly convex regularization and general data-fit functions. We develop an inertial approach of which we analyze both convergence and stability properties. Using tools from inexact proximal calculus, we prove early stopping results with optimal convergence rates for additive data terms and further consider more general cases, such as the Kullback--Leibler divergence, for which different type of proximal point approximations hold.


中文翻译:

通过双对角下降加速迭代正则化

SIAM优化杂志,第31卷,第1期,第754-784页,2021年1月。
我们提出并分析了一种加速迭代双对角下降算法,用于求解具有强凸正则化和通用数据拟合函数的线性反问题。我们开发了一种惯性方法,可以分析其收敛性和稳定性。使用不精确的近端演算中的工具,我们以加和数据项的最优收敛速度证明了早期停止结果,并进一步考虑了更通用的情况,例如Kullback-Leibler散度,其中存在不同类型的近端点近似值。
更新日期:2021-03-21
down
wechat
bug