Tensor Deli: Tensor Completion for Low CP-Rank Tensors via Random Sampling (2403.09932v1)
Abstract: We propose two provably accurate methods for low CP-rank tensor completion - one using adaptive sampling and one using nonadaptive sampling. Both of our algorithms combine matrix completion techniques for a small number of slices along with Jennrich's algorithm to learn the factors corresponding to the first two modes, and then solve systems of linear equations to learn the factors corresponding to the remaining modes. For order-$3$ tensors, our algorithms follow a "sandwich" sampling strategy that more densely samples a few outer slices (the bread), and then more sparsely samples additional inner slices (the bbq-braised tofu) for the final completion. For an order-$d$, CP-rank $r$ tensor of size $n \times \cdots \times n$ that satisfies mild assumptions, our adaptive sampling algorithm recovers the CP-decomposition with high probability while using at most $O(nr\log r + dnr)$ samples and $O(n2r2+dnr2)$ operations. Our nonadaptive sampling algorithm recovers the CP-decomposition with high probability while using at most $O(dnr2\log n + nr\log2 n)$ samples and runs in polynomial time. Numerical experiments demonstrate that both of our methods work well on noisy synthetic data as well as on real world data.
- Noise-tolerant life-long matrix completion via adaptive sampling. Advances in Neural Information Processing Systems, 29, 2016.
- Noisy tensor completion via the sum-of-squares hierarchy. In Conference on Learning Theory, pages 417–445. PMLR, 2016.
- 220 band aviris hyperspectral image data set: June 12, 1992 indian pine test site 3, Sep 2015.
- Uniqueness of tensor decompositions with applications to polynomial identifiability. In Conference on Learning Theory, pages 742–778. PMLR, 2014.
- A new sampling technique for tensors. arXiv preprint arXiv:1502.05023, 2015.
- Standard error of prediction for multilinear pls - 2. practical implementation in fluorescence spectroscopy. Chemometrics and Intelligent Laboratory Systems, 75:69–76, 01 2005.
- Nonconvex low-rank tensor completion from noisy data. Advances in neural information processing systems, 32, 2019.
- Yudong Chen. Incoherence-optimal matrix completion. IEEE Transactions on Information Theory, 61(5):2909–2923, 2015.
- Completing any low-rank matrix, provably. Journal of Machine Learning Research, 16(94):2999–3034, 2015.
- Tensor methods and recommender systems. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, 7(3):e1201, 2017.
- Solving low-rank matrix completion problems efficiently. In 2009 47th Annual Allerton Conference on Communication, Control, and Computing (Allerton), pages 1013–1020. IEEE, 2009.
- Tensor sandwich: Tensor completion for low cp-rank tensors via adaptive random sampling. In 2023 International Conference on Sampling Theory and Applications (SampTA), pages 1–6. IEEE, 2023.
- Provable tensor factorization with missing data. Advances in Neural Information Processing Systems, 27, 2014.
- Exact nuclear norm, completion and decomposition for random overcomplete tensors via degree-4 sos. arXiv preprint arXiv:2011.09416, 2020.
- Low-rank matrix and tensor completion via adaptive sampling. Advances in neural information processing systems, 26, 2013.
- A decomposition for three-way arrays. SIAM Journal on Matrix Analysis and Applications, 14(4):1064–1083, 1993.
- Hyperspectral tensor completion using low-rank modeling and convex functional analysis. IEEE Transactions on Neural Networks and Learning Systems, 2023.
- Tensor completion made practical. Advances in Neural Information Processing Systems, 33:18905–18916, 2020.
- Tensor completion for estimating missing values in visual data. IEEE transactions on pattern analysis and machine intelligence, 35(1):208–220, 2012.
- Low cp rank and tucker rank tensor completion for estimating missing components in image data. IEEE Transactions on Circuits and Systems for Video Technology, 30(4):944–954, 2019.
- Ankur Moitra. Algorithmic aspects of machine learning. Cambridge University Press, 2018.
- Spectral algorithms for tensor completion. Communications on Pure and Applied Mathematics, 71(11):2381–2425, 2018.
- Tensor completion with provable consistency and fairness guarantees for recommender systems. ACM Transactions on Recommender Systems, 1(3):1–26, 2023.
- Conic optimization via operator splitting and homogeneous self-dual embedding. Journal of Optimization Theory and Applications, 169(3):1042–1068, June 2016.
- Exact tensor completion with sum-of-squares. In Conference on Learning Theory, pages 1619–1673. PMLR, 2017.
- A non-backtracking method for long matrix and tensor completion. arXiv preprint arXiv:2304.02077, 2023.
- Short-term traffic prediction based on dynamic tensor completion. IEEE Transactions on Intelligent Transportation Systems, 17(8):2123–2133, 2016.
- Parafac and missing values. Chemometrics and Intelligent Laboratory Systems, 75:163–180, 2005.
- Interpolation using hankel tensor completion. In SEG Technical Program Expanded Abstracts 2013, pages 3634–3638. Society of Exploration Geophysicists, 2013.
- Anomaly detection of hyperspectral image via tensor completion. IEEE Geoscience and Remote Sensing Letters, 18(6):1099–1103, 2020.
- Accurate recovery of internet traffic data: A tensor completion approach. In IEEE INFOCOM 2016-The 35th Annual IEEE International Conference on Computer Communications, pages 1–9. IEEE, 2016.
- On tensor completion via nuclear norm minimization. Foundations of Computational Mathematics, 16(4):1031–1068, 2016.
- Anru Zhang. Cross: Efficient low-rank tensor completion. The Annals of Statistics, 47(2):936–964, 2019.
- Learning tensor low-rank prior for hyperspectral image reconstruction. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 12006–12015, 2021.
- Fairness-aware tensor-based recommendation. In Proceedings of the 27th ACM international conference on information and knowledge management, pages 1153–1162, 2018.