Signal recovery under generative neural network priors has emerged as a promising direction in statistical inference and computational imaging. Theoretical analysis of reconstruction algorithms under generative priors is, however, challenging. For generative priors with fully connected layers and Gaussian i.i.d. weights, this was achieved by the multi-layer approximate message (ML-AMP) algorithm via a rigorous state evolution. However, practical generative priors are typically convolutional, allowing for computational benefits and inductive biases, and so the Gaussian i.i.d. weight assumption is very limiting. In this paper, we overcome this limitation and establish the state evolution of ML-AMP for random convolutional layers. We prove in particular that random convolutional layers belong to the same universality class as Gaussian matrices. Our proof technique is of an independent interest as it establishes a mapping between convolutional matrices and spatially coupled sensing matrices used in coding theory.
翻译:基因神经网络前科下的信号恢复是统计推理和计算成像的一个大有希望的方向。但是,对基因前科下重建算法的理论分析具有挑战性。对于具有完全连接层和高西亚i.d.重量的基因前科分析来说,这是通过严格状态演化的多层近似电文(ML-AMP)算法(ML-AMP)实现的。但是,实际基因前科通常具有进化性,允许计算效益和进化偏差,因此Gaussian i.d.重量假设是非常有限的。在本文中,我们克服了这一限制,确定了ML-AMP对随机进化层的状态演变。我们特别证明,随机进化层属于与高斯矩阵相同的普遍性类别。我们的证据技术具有独立的兴趣,因为它建立了在编码理论中使用的进化矩阵和空间结合感测矩阵之间的绘图。