Abstract
In this paper, we study the problem of low-rank matrix sensing where the goal is to reconstruct a matrix exactly using a small number of linear measurements. Existing methods for the problem either rely on measurement operators such as random element-wise sampling which cannot recover arbitrary low-rank matrices or require the measurement operator to satisfy the Restricted Isometry Property (RIP). However, RIP based linear operators are generally full rank and require large computation/storage cost for both measurement (encoding) as well as reconstruction (decoding).
In this paper, we propose simple rank-one Gaussian measurement operators for matrix sensing that are significantly less expensive in terms of memory and computation for both encoding and decoding. Moreover, we show that the matrix can be reconstructed exactly using a simple alternating minimization method as well as a nuclear-norm minimization method. Finally, we demonstrate the effectiveness of the measurement scheme vis-a-vis existing RIP based methods.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Agarwal, A., Anandkumar, A., Jain, P., Netrapalli, P., Tandon, R.: Learning sparsely used overcomplete dictionaries via alternating minimization. COLT (2014)
Cai, T.T., Zhang, A., et al.: Rop: Matrix recovery via rank-one projections. The Annals of Statistics 43(1), 102–138 (2015)
Candès, E.J., Recht, B.: Exact matrix completion via convex optimization. Foundations of Computational Mathematics 9(6), 717–772 (2009)
Candès, E.J., Tao, T.: The power of convex relaxation: Near-optimal matrix completion. IEEE Trans. Inform. Theory 56(5), 2053–2080 (2009)
Chen, Y.: Incoherence-optimal matrix completion. arXiv preprint arXiv:1310.0154 (2013)
Gross, D.: Recovering low-rank matrices from few coefficients in any basis. IEEE Transactions on Information Theory 57(3), 1548–1566 (2011)
Hardt, M.: Understanding alternating minimization for matrix completion. In: Foundations 2014 IEEE 55th Annual Symposium on of Computer Science (FOCS), pp. 651–660. IEEE (2014)
Hardt, M., Wootters, M.: Fast matrix completion without the condition number. In: Proceedings of The 27th Conference on Learning Theory, pp. 638–678 (2014)
Hsieh, C.J., Dhillon, I.S., Ravikumar, P.K., Becker, S., Olsen, P.A.: Quic & dirty: A quadratic approximation approach for dirty statistical models. In: Advances in Neural Information Processing Systems, pp. 2006–2014 (2014)
Hsieh, C.J., Olsen, P.: Nuclear norm minimization via active subspace selection. In: Proceedings of The 31st International Conference on Machine Learning, pp. 575–583 (2014)
Jain, P., Dhillon, I.S.: Provable inductive matrix completion (2013). CoRR. http://arxiv.org/abs/1306.0626
Jain, P., Meka, R., Dhillon, I.S.: Guaranteed rank minimization via singular value projection. In: NIPS, pp. 937–945 (2010)
Jain, P., Netrapalli, P., Sanghavi, S.: Low-rank matrix completion using alternating minimization. In: STOC (2013)
Keshavan, R.H., Montanari, A., Oh, S.: Matrix completion from a few entries. IEEE Transactions on Information Theory 56(6), 2980–2998 (2010)
Kueng, R., Rauhut, H., Terstiege, U.: Low rank matrix recovery from rank one measurements. arXiv preprint arXiv:1410.6913 (2014)
Lee, K., Bresler, Y.: Guaranteed minimum rank approximation from linear observations by nuclear norm minimization with an ellipsoidal constraint. arXiv preprint arXiv:0903.4742 (2009)
Liu, Y.K.: Universal low-rank matrix recovery from pauli measurements. In: Advances in Neural Information Processing Systems, pp. 1638–1646 (2011)
Netrapalli, P., Niranjan, U., Sanghavi, S., Anandkumar, A., Jain, P.: Non-convex robust PCA. In: Advances in Neural Information Processing Systems, pp. 1107–1115 (2014)
Recht, B.: A simpler approach to matrix completion. The Journal of Machine Learning Research 12, 3413–3430 (2011)
Recht, B., Fazel, M., Parrilo, P.A.: Guaranteed minimum-rank solutions of linear matrix equations via nuclear norm minimization. SIAM Review 52(3), 471–501 (2010)
Tropp, J.A.: User-friendly tail bounds for sums of random matrices. Foundations of Computational Mathematics 12(4), 389–434 (2012)
Xu, M., Jin, R., Zhou, Z.H.: Speedup matrix completion with side information: application to multi-label learning. In: Advances in Neural Information Processing Systems, pp. 2301–2309 (2013)
Yu, H.F., Hsieh, C.J., Si, S., Dhillon, I.S.: Scalable coordinate descent approaches to parallel matrix factorization for recommender systems. In: ICDM, pp. 765–774 (2012)
Yu, H.F., Jain, P., Kar, P., Dhillon, I.S.: Large-scale multi-label learning with missing labels. In: Proceedings of The 31st International Conference on Machine Learning, pp. 593–601 (2014)
Zuk, O., Wagner, A.: Low-rank matrix recovery from row-and-column affine measurements. In: Proceedings of the 32nd International Conference on Machine Learning, ICML 2015, Lille, France, 6–11 July 2015, pp. 2012–2020 (2015)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Zhong, K., Jain, P., Dhillon, I.S. (2015). Efficient Matrix Sensing Using Rank-1 Gaussian Measurements. In: Chaudhuri, K., GENTILE, C., Zilles, S. (eds) Algorithmic Learning Theory. ALT 2015. Lecture Notes in Computer Science(), vol 9355. Springer, Cham. https://doi.org/10.1007/978-3-319-24486-0_1
Download citation
DOI: https://doi.org/10.1007/978-3-319-24486-0_1
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-24485-3
Online ISBN: 978-3-319-24486-0
eBook Packages: Computer ScienceComputer Science (R0)