Timezone: »

Convolutional Imputation of Matrix Networks
Qingyun Sun · Mengyuan Yan · David Donoho · stephen boyd

Fri Jul 13 09:15 AM -- 12:00 PM (PDT) @ Hall B #70

A matrix network is a family of matrices, with their relations modeled as a weighted graph. We consider the task of completing a partially observed matrix network. The observation comes from a novel sampling scheme where a fraction of matrices might be completely unobserved. How can we recover the entire matrix network from incomplete observations? This mathematical problem arises in many applications including medical imaging and social networks. To recover the matrix network, we propose a structural assumption that the matrices are low-rank after the graph Fourier transform on the network. We formulate a convex optimization problem and prove an exact recovery guarantee for the optimization problem. Furthermore, we numerically characterize the exact recovery regime for varying rank and sampling rate and discover a new phase transition phenomenon. Then we give an iterative imputation algorithm to efficiently solve optimization problem and complete large scale matrix networks. We demonstrate the algorithm with a variety of applications such as MRI and Facebook user network.

Author Information

Qingyun Sun (Stanford University)
Mengyuan Yan (Stanford University)
David Donoho (Stanford University)
stephen boyd (stanford university)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors