Near-optimal stochastic approximation for online principal component estimation
نویسندگان
چکیده
منابع مشابه
Diffusion Approximations for Online Principal Component Estimation and Global Convergence
In this paper, we propose to adopt the diffusion approximation tools to study the dynamics of Oja’s iteration which is an online stochastic gradient descent method for the principal component analysis. Oja’s iteration maintains a running estimate of the true principal component from streaming data and enjoys less temporal and spatial complexities. We show that the Oja’s iteration for the top ei...
متن کاملLongitudinal functional principal component modeling via Stochastic Approximation Monte Carlo.
The authors consider the analysis of hierarchical longitudinal functional data based upon a functional principal components approach. In contrast to standard frequentist approaches to selecting the number of principal components, the authors do model averaging using a Bayesian formulation. A relatively straightforward reversible jump Markov Chain Monte Carlo formulation has poor mixing properti...
متن کاملLongitudinal functional principal component modelling via Stochastic Approximation Monte Carlo
The authors consider the analysis of hierarchical longitudinal functional data based upon a functional principal components approach. In contrast to standard frequentist approaches to selecting the number of principal components, the authors domodel averaging using a Bayesian formulation. A relatively straightforward reversible jumpMarkovChainMonte Carlo formulation has poormixing properties an...
متن کاملOnline Principal Component Analysis
We consider the online version of the well known Principal Component Analysis (PCA) problem. In standard PCA, the input to the problem is a set of vectors X = [x1, . . . , xn] in Rd×n and a target dimension k < d; the output is a set of vectors Y = [y1, . . . , yn] in Rk×n that minimize minΦ ‖X − ΦY ‖F where Φ is restricted to be an isometry. The global minimum of this quantity, OPTk, is obtain...
متن کاملApproximation bounds for sparse principal component analysis
We produce approximation bounds on a semidefinite programming relaxation for sparse principal component analysis. These bounds control approximation ratios for tractable statistics in hypothesis testing problems where data points are sampled from Gaussian models with a single sparse leading component. We study approximation bounds for a semidefinite relaxation of the sparse eigenvalue problem, ...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Mathematical Programming
سال: 2017
ISSN: 0025-5610,1436-4646
DOI: 10.1007/s10107-017-1182-z