dc.contributor.author | Chen, Yuxin | |
dc.date.accessioned | 2019-09-18T19:16:47Z | |
dc.date.available | 2019-09-18T19:16:47Z | |
dc.date.issued | 2019-09-05 | |
dc.identifier.uri | http://hdl.handle.net/1853/61861 | |
dc.description | Presented on September 5, 2019 at 11:00 a.m. in the Groseclose Building, Room 402. | en_US |
dc.description | Yuxin Chen is an Assistant Professor of Electrical Engineering at Princeton University. His research interests include high-dimensional estimation, machine learning, convex and nonconvex optimization, information theory, statistics, statistical signal processing, network science, and their applications in medical imaging and computational biology. | en_US |
dc.description | Runtime: 51:22 minutes | en_US |
dc.description.abstract | Noisy matrix completion aims at estimating a low-rank matrix given only partial and corrupted entries. Despite substantial progress in designing efficient estimation algorithms, it remains largely unclear how to assess the uncertainty of the obtained estimates and how to perform statistical inference on the unknown matrix (e.g. constructing a valid and short confidence interval for an unseen entry).
This talk takes a step towards inference and uncertainty quantification for noisy matrix completion. We develop a simple procedure to compensate for the bias of the widely used convex and nonconvex estimators. The resulting de-biased estimators admit nearly precise non-asymptotic distributional characterizations, which in turn enable optimal construction of confidence intervals / regions for, say, the missing entries and the low-rank factors. Our inferential procedures do not rely on sample splitting, thus avoiding unnecessary loss of data efficiency. As a byproduct, we obtain a sharp characterization of the estimation accuracy of our de-biased estimators, which, to the best of our knowledge, are the first tractable algorithms that provably achieve full statistical efficiency (including the preconstant). The analysis herein is built upon the intimate link between convex and nonconvex optimization.
This is joint work with Cong Ma, Yuling Yan, Yuejie Chi, and Jianqing Fan. | en_US |
dc.format.extent | 51:22 minutes | |
dc.language.iso | en_US | en_US |
dc.relation.ispartofseries | TRIAD Distinguished Lecture Series | en_US |
dc.subject | Confidence intervals | en_US |
dc.subject | Matrix completion | en_US |
dc.subject | Uncertainty quantification | en_US |
dc.title | Lecture 5: Inference and Uncertainty Quantification for Noise Matrix Completion | en_US |
dc.type | Lecture | en_US |
dc.type | Video | en_US |
dc.contributor.corporatename | Georgia Institute of Technology. Transdisciplinary Research Institute for Advancing Data Science | en_US |
dc.contributor.corporatename | Princeton University. Dept. of Electrical Engineering | en_US |