Seeking consensus on subspaces in federated principal component analysis
From MaRDI portal
Publication:6636797
DOI10.1007/S10957-024-02523-1MaRDI QIDQ6636797
Publication date: 12 November 2024
Published in: Journal of Optimization Theory and Applications (Search for Journal in Brave)
principal component analysisalternating direction method of multipliersorthogonality constraintsfederated learning
Cites Work
- Title not available (Why is that?)
- A practical relative error criterion for augmented Lagrangians
- Simultaneous iteration for computing invariant subspaces of non-Hermitian matrices
- Global convergence of ADMM in nonconvex nonsmooth optimization
- Primal-dual optimization algorithms over Riemannian manifolds: an iteration complexity analysis
- Simultaneous iteration method for symmetric matrices
- Exact matrix completion via convex optimization
- Limited memory block Krylov subspace optimization for computing dominant singular value decompositions
- The Algorithmic Foundations of Differential Privacy
- A Simultaneous Iteration Algorithm for Real Matrices
- Principal component analysis in linear systems: Controllability, observability, and model reduction
- A Distributed Framework for Dimensionality Reduction and Denoising
- $rm K$-SVD: An Algorithm for Designing Overcomplete Dictionaries for Sparse Representation
- A New First-Order Algorithmic Framework for Optimization Problems with Orthogonality Constraints
- On the Nonergodic Convergence Rate of an Inexact Augmented Lagrangian Framework for Composite Convex Programming
- An Efficient Gauss--Newton Algorithm for Symmetric Low-Rank Product Matrix Approximations
- Privacy-preserving decentralised singular value decomposition
- Decentralized optimization over the Stiefel manifold by an approximate augmented Lagrangian function
- FAST-PCA: a fast and exact algorithm for distributed principal component analysis
This page was built for publication: Seeking consensus on subspaces in federated principal component analysis
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6636797)
