Communication-Efficient Distributed Eigenspace Estimation
DOI10.1137/20M1364862zbMath1476.62198arXiv2009.02436OpenAlexW3203712890MaRDI QIDQ5162627
Vasileios Charisopoulos, Austin R. Benson, Anil Damle
Publication date: 3 November 2021
Published in: SIAM Journal on Mathematics of Data Science (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/2009.02436
Computational methods for problems pertaining to statistics (62-08) Factor analysis and principal components; correspondence analysis (62H25) Numerical computation of eigenvalues and eigenvectors of matrices (65F15) Inference from stochastic processes and spectral analysis (62M15) Probability in computer science (algorithm analysis, random structures, phase transitions, etc.) (68Q87) Numerical methods for low-rank matrix approximation; matrix compression (65F55)
Uses Software
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Low rank matrix recovery from rank one measurements
- The symmetric Procrustes problem
- Principal component analysis.
- Second order accurate distributed eigenvector computation for extremely large matrices
- Distributed estimation of principal eigenspaces
- Frequent Directions: Simple and Deterministic Matrix Sketching
- On a Perturbation Bound for Invariant Subspaces of Matrices
- Exact and Stable Covariance Estimation From Quadratic Sampling via Convex Programming
- Phase Retrieval via Wirtinger Flow: Theory and Algorithms
- Spectral Algorithms
- On the optimality of averaging in distributed statistical learning
- High-Dimensional Statistics
- High-Dimensional Probability
- Distributed Subgradient Methods for Multi-Agent Optimization
- The Byzantine generals problem
- Uniform Bounds for Invariant Subspace Perturbations
- Optimal Algorithms for Non-Smooth Distributed Optimization in Networks
- Communication-Efficient Distributed Statistical Inference
- Nonconvex Optimization Meets Low-Rank Matrix Factorization: An Overview
- Dual Averaging for Distributed Optimization: Convergence Analysis and Network Scaling
- Turning Big data into tiny data: Constant-size coresets for k-means, PCA and projective clustering
- A dual approach for optimal algorithms in distributed optimization over networks
- Distributed Estimation for Principal Component Analysis: An Enlarged Eigenspace Analysis
This page was built for publication: Communication-Efficient Distributed Eigenspace Estimation