论文标题
凸正规化器的迭代正则化
Iterative regularization for convex regularizers
论文作者
论文摘要
我们研究线性模型的迭代正则化，当偏差为凸时，但不一定强烈凸。我们表征了基于基于双重梯度的方法的稳定性，并在存在最坏情况的确定性噪声的情况下分析了其收敛性。作为一个主要示例，我们专注于稀疏恢复问题的问题。我们分析的关键是在存在错误的情况下正规化理论和优化的思想结合。实验表明，通过相当大的计算加速可以实现最先进的性能，理论结果得到了补充。
We study iterative regularization for linear models, when the bias is convex but not necessarily strongly convex. We characterize the stability properties of a primal-dual gradient based approach, analyzing its convergence in the presence of worst case deterministic noise. As a main example, we specialize and illustrate the results for the problem of robust sparse recovery. Key to our analysis is a combination of ideas from regularization theory and optimization in the presence of errors. Theoretical results are complemented by experiments showing that state-of-the-art performances can be achieved with considerable computational speed-ups.
