...
机译:通过梯度下降的卷积相位检索
Columbia Univ Dept Elect Engn New York NY 10027 USA|Columbia Univ Data Sci Inst New York NY 10027 USA|NYU Ctr Data Sci New York NY 10011 USA;
Columbia Univ Dept Elect Engn New York NY 10027 USA|Columbia Univ Data Sci Inst New York NY 10027 USA|Cornell Univ Dept Comp Sci Ithaca NY 14853 USA;
Weizmann Inst Sci Weizmann Fac Math & Comp Sci IL-7610001 Rehovot Israel;
Columbia Univ Dept Elect Engn New York NY 10027 USA|Columbia Univ Data Sci Inst New York NY 10027 USA|Columbia Univ Dept Appl Phys & Appl Math New York NY 10027 USA;
Convolution; Diffraction; Phase measurement; Complexity theory; Random variables; Optical diffraction; Convolutional codes; Phase retrieval; nonconvex optimization; nonlinear inverse problem; circulant convolution;
机译:非耦合统计估计中的隐式正常化:梯度下降融合为相位检索,矩阵完成和盲解卷积
机译:随机初始化的梯度下降:非透露阶段检索的快速全局收敛
机译:广义阶段检索问题的梯度下降算法的全局融合
机译:具有生成先验的交替相位投影梯度下降,用于解决压缩相位检索
机译:一种改进的噪声阶段检索双阶层血管算法
机译:基于互动信息的学习速率衰减用于深神经网络的随机梯度血统训练
机译:广义相位检索问题的梯度下降算法