1 / 11

Imputation of Streaming Low-Rank Tensor Data

Morteza Mardani , Gonzalo Mateos and Georgios Giannakis ECE Department, University of Minnesota Acknowledgment : AFOSR MURI grant no. FA9550-10-1-0567. Imputation of Streaming Low-Rank Tensor Data. A Coruna, Spain June 25, 2013. 1. Learning from “Big Data”.

graham
Download Presentation

Imputation of Streaming Low-Rank Tensor Data

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. MortezaMardani, Gonzalo Mateos and GeorgiosGiannakis ECE Department, University of Minnesota Acknowledgment: AFOSR MURI grant no. FA9550-10-1-0567 Imputation of Streaming Low-Rank Tensor Data A Coruna, Spain June 25, 2013 1

  2. Learning from “Big Data” `Data are widely available, what is scarce is the ability to extract wisdom from them’ Hal Varian, Google’s chief economist Fast BIG Productive Ubiquitous Revealing Messy Smart 2 K. Cukier, ``Harnessing the data deluge,'' Nov. 2011.

  3. Tensor model • Data cube • PARAFAC decomposition cr br ar B= C= A= βi αi γi

  4. Streaming tensor data • Streaming data • Tensor subspace comprises R rank-one matrices Goal: given the streaming data , at time t learn the subspace matrices (At,Bt) and impute the missing entries of Yt?

  5. Prior art • Matrix/tensor subspace tracking • Projection approximation (PAST) [Yang’95] • Misses: rank regularization [Mardani et al’13], GROUSE [Balzano et al’10] • Outliers: [Mateos et al’10], GRASTA [He et al’11] • Adaptive LS tensor tracking [Nion et al’09] with full data; tensor slices treated as long vectors • Batch tensor completion [Juan et al’13], [Gandy et al’11] • Novelty:Online rank regularization with misses • Tensor decomposition/imputation • Scalable and provably convergent iterates

  6. Batch tensor completion • Rank-regularized formulation [Juan et al’13] (P1) • Tikhonovregularizerpromotes low rank Proposition 1[Juan et al’13]: Let , then

  7. Tensor subspace tracking • Exponentially-weighted LS estimator (P2) ft(A,B) • ``on-the-fly’’ imputation • Alternating minimization with stochastic gradient iterations (at time t) • Step1:Projection coefficientupdates • Step2: Subspace update • O(|Ωt|R2) operations per iteration M. Mardani, G. Mateos, and G. B. Giannakis, “Subspace learning and imputation for streaming Big Data matrices and tensors,"IEEE Trans. Signal Process., Apr. 2014 (submitted).

  8. Convergence • As1) Invariant subspace and • As2) Infinite memory β= 1 Proposition 2: If and are i.i.d., and c1) is uniformly bounded; c2) is in a compact set; and c3) is strongly convex w.r.t. hold, then almost surely (a. s.) • asymptotically converges to a st.point of batch(P1)

  9. Cardiac MRI • FOURDIX dataset • 263 images of 512 x 512 • Y: 32 x 32 x 67,328 • 75% misses • R=10  ex=0.14 • R=50  ex=0.046 (b) (a) (c) (d) Ground truth, (b) acquired image; reconstructed for R=10 (c), R=50 (d) http://www.osirix-viewer.com/datasets.

  10. Tracking traffic anomalies • Link load measurements • Internet-2 backbone network • Yt: weighted adjacency matrix • Available data Y: 11x11x6,048 • 75% misses, R=18 http://internet2.edu/observatory/archive/data-collections.html

  11. Conclusions • Real-time subspace trackers for decomposition/imputation • Streaming big and incomplete tensor data • Provably convergent scalable algorithms • Applications • Reducing the MRI acquisition time • Unveiling network traffic anomalies for Internet backbone networks • Ongoing research • Incorporating spatiotemporal correlation information via kernels • Accelerated stochastic-gradient for subspace update

More Related