More Like this

1. DP-PCA: Statistically Optimal and Differentially Private PCA

   Xiyang Liu, Weihao Kong (January 2022, arXivorg)
2. Low-Precision Streaming PCA

   Dasgupta, Sanjoy; Kumar, Syamantak; Pandey, Shourya; Sarkar, Purnamrita (January 2026, Advances of Neural Information Processing Systems 2025.)
3. Streaming PCA for Markovian Data

   Syamantak Kumar, Purnamrita Sarkar (June 2023, arXivorg)
4. Streaming PCA for Markovian Data

   Kumar, Syamantak; Sarkar, Purnamrita (January 2024, NeurIPS)
5. Robust PCA by Manifold Optimization

   Zhang, Teng; Yang, Yi (November 2018, Journal of machine learning research)

   Robust PCA is a widely used statistical procedure to recover an underlying low-rank matrix with grossly corrupted observations. This work considers the problem of robust PCA as a nonconvex optimization problem on the manifold of low-rank matrices and proposes two algorithms based on manifold optimization. It is shown that, with a properly designed initialization, the proposed algorithms are guaranteed to converge to the underlying lowrank matrix linearly. Compared with a previous work based on the factorization of low-rank matrices Yi et al. (2016), the proposed algorithms reduce the dependence on the condition number of the underlying low-rank matrix theoretically. Simulations and real data examples con rm the competitive performance of our method. 

   more » « less