2000 character limit reached
Efficient Federated Low Rank Matrix Recovery via Alternating GD and Minimization: A Simple Proof (2306.17782v2)
Published 30 Jun 2023 in cs.IT and math.IT
Abstract: This note provides a significantly simpler and shorter proof of our sample complexity guarantee for solving the low rank column-wise sensing problem using the Alternating Gradient Descent (GD) and Minimization (AltGDmin) algorithm. AltGDmin was developed and analyzed for solving this problem in our recent work. We also provide an improved guarantee.
- S. Babu, S. G. Lingala, and N. Vaswani, “Fast low rank compressive sensing for accelerated dynamic MRI,” IEEE Trans. Comput. Imaging, 2023.
- S. S. Du, W. Hu, S. M. Kakade, J. D. Lee, and Q. Lei, “Few-shot learning via learning the representation, provably,” in Intnl. Conf. Learning Representations (ICLR), 2021.
- S. Nayer and N. Vaswani, “Fast and sample-efficient federated low rank matrix recovery from column-wise linear and quadratic projections,” IEEE Trans. Info. Th., Feb. 2023.
- P. Netrapalli, P. Jain, and S. Sanghavi, “Low-rank matrix completion using alternating minimization,” in Annual ACM Symp. on Th. of Comp. (STOC), 2013.
- X. Yi, D. Park, Y. Chen, and C. Caramanis, “Fast algorithms for robust pca via gradient descent,” in Neur. Info. Proc. Sys. (NeurIPS), 2016.
- C. Ma, K. Wang, Y. Chi, and Y. Chen, “Implicit regularization in nonconvex statistical estimation: Gradient descent converges linearly for phase retrieval, matrix completion and blind deconvolution,” in Intl. Conf. Machine Learning (ICML), 2018.
- S. Nayer and N. Vaswani, “Sample-efficient low rank phase retrieval,” IEEE Trans. Info. Th., Dec. 2021.
- Y. Cherapanamjeri, K. Gupta, and P. Jain, “Nearly-optimal robust matrix completion,” ICML, 2016.
- P.-Å. Wedin, “Perturbation bounds in connection with singular value decomposition,” BIT Numerical Mathematics, vol. 12, no. 1, pp. 99–111, 1972.