论文标题
ADA-LISTA：学习的求解器适应不同的模型
Ada-LISTA: Learned Solvers Adaptive to Varying Models
论文作者
论文摘要
基于迭代求解器的展开的神经网络，例如Lista（学习的迭代软阈值算法），由于其加速性能而被广泛使用。然而，与未学习的求解器相反，这些网络是在某个词典上训练的，因此它们不适合不同的模型场景。这项工作介绍了一个自适应学习的求解器，称为ADA-LISTA，该求解器接收到一对信号及其相应的词典作为输入，并学习了一种通用体系结构来为它们提供服务。我们证明，该方案可以保证为不同模型（包括字典扰动和排列）以线性速率求解稀疏编码。我们还提供了一项广泛的数值研究，证明了其实际适应能力。最后，我们将ada-lista部署到自然图像上，其中贴片面罩在空间上变化，因此需要这种适应性。
Neural networks that are based on unfolding of an iterative solver, such as LISTA (learned iterative soft threshold algorithm), are widely used due to their accelerated performance. Nevertheless, as opposed to non-learned solvers, these networks are trained on a certain dictionary, and therefore they are inapplicable for varying model scenarios. This work introduces an adaptive learned solver, termed Ada-LISTA, which receives pairs of signals and their corresponding dictionaries as inputs, and learns a universal architecture to serve them all. We prove that this scheme is guaranteed to solve sparse coding in linear rate for varying models, including dictionary perturbations and permutations. We also provide an extensive numerical study demonstrating its practical adaptation capabilities. Finally, we deploy Ada-LISTA to natural image inpainting, where the patch-masks vary spatially, thus requiring such an adaptation.
