Deep unfolding networks have recently gained popularity for solving imaging inverse problems. However, the computational and memory complexity of data-consistency layers within traditional deep unfolding networks scales with the number of measurements, limiting their applicability to large-scale imaging inverse problems. We propose SGD-Net as a new methodology for improving the efficiency of deep unfolding through stochastic approximations of the data-consistency layers. Our theoretical analysis shows that SGD-Net can be trained to approximate batch deep unfolding networks to an arbitrary precision. Our simulations on intensity diffraction tomography and sparse-view computed tomography show that SGD-Net can match the performance of the traditional batch network at a fraction of training and testing complexity.

中文翻译：

---

SGD-Net：具有理论保证的高效基于模型的深度学习


深度展开网络最近在解决成像逆问题方面广受欢迎。然而，传统深度展开网络中数据一致性层的计算和存储复杂性随着测量数量的增加而变化，限制了它们对大规模成像反演问题的适用性。我们提出 SGD-Net 作为一种新方法，通过数据一致性层的随机近似来提高深度展开的效率。我们的理论分析表明，SGD-Net 可以经过训练以将批量深度展开网络近似到任意精度。我们对强度衍射断层扫描和稀疏视图计算机断层扫描的模拟表明，SGD-Net 可以与传统批处理网络的性能相匹配，而训练和测试复杂性只需一小部分。