Stochastic Optimization of PCA with Capped MSG
Not on the map. Why?
Abstract (arXiv)
We study PCA as a stochastic optimization problem and propose a novel stochastic approximation algorithm which we refer to as "Matrix Stochastic Gradient" (MSG), as well as a practical variant, Capped MSG. We study the method both theoretically and empirically.
Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). First posted on arXiv 5 Jul 2013.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 4; 2022: 0; 2023: 2.
6 papers.
- 2021Fast and Efficient MMD-based Fair PCA via Optimization over Stiefel Manifoldcited by 18
- 2021A Linearly Convergent Algorithm for Distributed Principal Component Analysiscited by 8
- 2023Streaming Kernel PCA Algorithm With Small Spacecited by 5
- 2021FedPower: Privacy-Preserving Distributed Eigenspace Estimationcited by 4
- 2021FAST-PCA: A Fast and Exact Algorithm for Distributed Principal Component Analysiscited by 3
- 2023When Collaborative Filtering is not Collaborative: Unfairness of PCA for Recommendationscited by 1
- 2023When Collaborative Filtering is not Collaborative: Unfairness of PCA for Recommendations15 Oct 2023
- 2023Streaming Kernel PCA Algorithm With Small Space8 Mar 2023
- 2021Fast and Efficient MMD-based Fair PCA via Optimization over Stiefel Manifold23 Sep 2021
- 2021FAST-PCA: A Fast and Exact Algorithm for Distributed Principal Component Analysis27 Aug 2021
- 2021FedPower: Privacy-Preserving Distributed Eigenspace Estimation1 Mar 2021
- 2021A Linearly Convergent Algorithm for Distributed Principal Component Analysis5 Jan 2021