We propose a general framework for reconstructing and denoising single entries of incomplete and noisy entries. We describe: effective algorithms for deciding if and entry can be reconstructed and, if so, for reconstructing and denoising it; and a priori bounds on the error of each entry, individually. In the noiseless case our algorithm is exact. For rank-one matrices, the new algorithm is fast, admits a highly-parallel implementation, and produces an error minimizing estimate that is qualitatively close to our theoretical and the state-of-the-art Nuclear Norm and OptSpace methods.
Franz J Kiraly (TU Berlin)
Louis Theran (Freie Universität Berlin)
More from the Same Authors
2018 : skpro: A domain-agnostic modelling framework for probabilistic supervised learning »
Franz J Kiraly