An Efficient Adaptive Minor Subspace Extraction Using Exact Nested Orthogonal Complement Structure
スポンサーリンク
概要
- 論文の詳細を見る
This paper presents a new adaptive minor subspace extraction algorithm based on an idea of Peng and Yi (07) for approximating the single minor eigenvector of a covariance matrix. By utilizing the idea inductively in the nested orthogonal complement subspaces, the proposed algorithm succeeds to relax the numerical sensitivity which has been annoying conventional adaptive minor subspace extraction algorithms for example, Oja algorithm (82) and its stabilized version: O-Oja algorithm (02). Simulation results demonstrate that the proposed algorithm realizes more stable convergence than O-Oja algorithm.
- （社）電子情報通信学会の論文
- 2008-08-01
著者
-
Yamada Isao
Dept. Of Communications & Integrated Systems Tokyo Institute Of Technology
-
Yamada Isao
Dept. Communications And Integrated Systems Tokyo Institute Of Technology
-
MISONO Masaki
Dept. of Communications & Integrated Systems, Tokyo Institute of Technology
-
Misono Masaki
Dept. Of Communications & Integrated Systems Tokyo Institute Of Technology
関連論文
- An Iterative MPEG Super-Resolution with an Outer Approximation of Framewise Quantization Constraint(Image)
- Discrete Time-Frequency Projection Filtering Based on an Alias-Free Discrete Time-Frequency Analysis(Digital Signal Processing)
- A Truncated Polynomial Interpolation and Its Application to Polynomially WLS Design of IIR Filters(Digital Signal Processing)
- A higher order generalization of an alias-free discrete time-frequency analysis
- A truncated polynomial interpolation theorem and its application to the WLS design of IIR filters
- A Super Resolution Reconstruction of MPEG Compressed Video Sequences
- An Edge-Preserving Super-Precision for Simultaneous Enhancement of Spacial and Grayscale Resolutions
- Blind and Nonblind DS/CDMA Receivers by Adaptive Projected Subgradient Method
- An Efficient Distributed Power Control for Infeasible Downlink Scenarios : Global-Local Fixed-Point-Approximation Technique(Papers Selected from the 20th Symposium on Signal Processing)
- A-4-14 MULTI-DOMAIN ADAPTIVE LEARNING
- Spectrum Estimation as a Problem of Finding Symmetric Positive Definite Block Toeplitz Matrices by the Hybrid Steepest Descent Method
- An Optimal Design of Signal Adapted Orthonormal Wavelet by The Hybrid Steepest Descent Method
- Fast and efficient interference suppression by uniform linear array based on dual-domain adaptive filtering technique (通信方式)
- Fast and efficient interference suppression by uniform linear array based on dual-domain adaptive filtering technique (回路とシステム)
- Fast and efficient interference suppression by uniform linear array based on dual-domain adaptive filtering technique (信号処理)
- An Efficient Adaptive Minor Subspace Extraction Using Exact Nested Orthogonal Complement Structure
- Inconsistent Convex Feasibility Problem with Multiple and Prioritized Hard Constraints
- A Numerically Robust Hybrid Steepest Descent Method
- A Deep Monotone Approximation Operator Based on the Best Quadratic Lower Bound of Convex Functions
- A-4-24 IMAGE RECOVERY BY HIERARCHICAL CONVEX OPTIMIZATION