.png){kind=icon}
.png){kind=icon}
Return
Subspace Estimation From Incomplete Observations: A High-Dimensional Analysis
.png){kind=icon}
OA
AI
DOI：10.1109/JSTSP.2018.2877405.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
We present a high-dimensional analysis of three popular algorithms, namely, Oja's method, GROUSE, and PETRELS, for subspace estimation from streaming and highly incomplete observations. We show that, with proper time scaling, the timevarying principal angles between the true subspace and its estimates given by the algorithms converge weakly to deterministic processes when the ambient dimension n tends to infinity. Moreover, the limiting processes can be exactly characterized as the unique solutions of certain ordinary differential equations (ODEs). A finite sample bound is also given showing that the rate of convergence toward such limits is O(1/root n). In addition to providing asymptotically exact predictions of the dynamic performance of the algorithms, our high-dimensional analysis yields several insights, including an asymptotic equivalence between Oja's method and GROUSE, and a precise scaling relationship linking the amount of missing data to the signal-to-noise ratio. By analyzing the solutions of the limitingODEs, we also establish phase transition phenomena associated with the steady-state performance of these techniques.
Keywords:
Subspace tracking
streaming PCA
incomplete data
high-dimensional analysis
scaling limit
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
13.7
Papers:
1.9K
Citations:
1.1W