No article text was recorded for this version.
top-k eigenvector estimation
Version 1 of 144 papers46 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Large-Scale Sparse Principal Component Analysis with Application to Text Data
- Blog: An Inverse-free Truncated Rayleigh-Ritz Method for Sparse Generalized Eigenvalue Problem
- Blog: Efficient Sparse PCA via Block-Diagonalization
- Blog: A near-optimal algorithm for differentially-private principal components
- Blog: A Simple and Provable Algorithm for Sparse Diagonal CCA
- Blog: Online Learning of Eigenvectors
- Blog: Faster Kernel Matrix Algebra via Density Estimation
- Blog: Oja's Algorithm for Streaming Sparse PCA
- Blog: Bootstrapping the Error of Oja's Algorithm
- Blog: Streaming PCA: Matching Matrix Bernstein and Near-Optimal Finite Sample Guarantees for Oja's Algorithm
- Blog: Convergence Analysis of Gradient Descent for Eigenvector Computation
- Blog: Minimax Rates of Estimation for Sparse PCA in High Dimensions
- Blog: The Fast Convergence of Incremental PCA
- Blog: Spectral Guarantees for Adversarial Streaming PCA
- Blog: Towards a theoretical analysis of PCA for heteroscedastic data
- Blog: Noisy Dual Principal Component Pursuit
- Blog: Streaming k-PCA: Efficient guarantees for Oja's algorithm, beyond rank-one updates
- Blog: On the Regret Minimization of Nonconvex Online Gradient Ascent for Online PCA
- Blog: Generalized Eigenvalue Problems with Generative Priors
- Blog: Gen-Oja: Simple & Efficient Algorithm for Streaming Generalized Eigenvector Computation
- Blog: Approximating the Top Eigenvector in Random Order Streams
- Blog: Sparse PCA on fixed-rank matrices
- Blog: Optimal Solutions for Sparse Principal Component Analysis
- Blog: Diffusion Approximations for Online Principal Component Estimation and Global Convergence
- Blog: Matching Matrix Bernstein with Little Memory: Near-Optimal Finite Sample Guarantees for Oja's Algorithm
- Blog: Robust Shift-and-Invert Preconditioning: Faster and More Sample Efficient Algorithms for Eigenvector Computation
- Blog: High-dimensional analysis of semidefinite relaxations for sparse principal components
- Blog: Sketching for Principal Component Regression
- Blog: Follow the Compressed Leader: Faster Online Learning of Eigenvectors and Faster MMWU
- Blog: Communication-efficient Algorithms for Distributed Stochastic Principal Component Analysis
- Blog: A Note on Sparse Generalized Eigenvalue Problem
- Blog: Approximation bounds for sparse principal component analysis
- Blog: Convergence of Stochastic Gradient Descent for PCA
- Blog: Distributed Estimation for Principal Component Analysis: An Enlarged Eigenspace Analysis
- Blog: High Dimensional Semiparametric Latent Graphical Model for Mixed Data
- Blog: Near-optimal stochastic approximation for online principal component estimation
- Blog: DP-PCA: Statistically Optimal and Differentially Private PCA
- Blog: Stochastic Variance-Reduced Algorithms for PCA with Arbitrary Mini-Batch Sizes
- Blog: Streaming Sparse Principal Component Analysis
- Blog: Faster Kernel Matrix Algebra via Density Estimation
- Blog: Support Recovery in Sparse PCA with General Missing Data
- Blog: Streaming Principal Component Analysis in Noisy Settings
- Blog: Global Convergence of Adaptive Sensing for Principal Eigenvector Estimation
- Blog: Transelliptical Component Analysis
History & citation
Current · Permanent link
- This direction split from Subspace Estimation Beyond the Leading Eigenvector (61% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_top_k_eigenvector_estimation_d4db9db0,
title = {top-k eigenvector estimation},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/top-k-eigenvector-estimation/rdr_d4db9db0e92b4303a1393fbab2304536},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-22},
}This exact version (version 1, frozen text):
@misc{lacuna_top_k_eigenvector_estimation_d4db9db0_v1,
title = {top-k eigenvector estimation},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/top-k-eigenvector-estimation/rdr_d4db9db0e92b4303a1393fbab2304536/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-22},
}