arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1607.05966cs.ITcs.LGmath.ITstat.ML
收藏

稀疏线性逆问题的Onsager校正深度学习

Onsager-corrected deep learning for sparse linear inverse problems

The Ohio State University(俄亥俄州立大学)

Mark Borgerding, Philip Schniter

摘要:

深度学习由于在许多推理问题上的广泛成功而获得了极大的普及。我们考虑将深度学习应用于压缩感知中遇到的稀疏线性逆问题,其中寻求从少量噪声线性测量中恢复稀疏信号。在本文中,我们提出了一种新的神经网络架构,它以近似消息传递(AMP)算法在迭代过程中消除预测误差的相同方式跨层消除预测误差:通过Onsager校正。数值实验表明,我们的“学习AMP”网络显着提高了Gregor和LeCun的“学习ISTA”网络的准确性和复杂性。

英文摘要:

Deep learning has gained great popularity due to its widespread success on many inference problems. We consider the application of deep learning to the sparse linear inverse problem encountered in compressive sensing, where one seeks to recover a sparse signal from a small number of noisy linear measurements. In this paper, we propose a novel neural-network architecture that decouples prediction errors across layers in the same way that the approximate message passing (AMP) algorithm decouples them across iterations: through Onsager correction. Numerical experiments suggest that our "learned AMP" network significantly improves upon Gregor and LeCun's "learned ISTA" network in both accuracy and complexity.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑