R.I.P.
👻
Ghosted
Efficient coordinate-wise leading eigenvector computation
February 25, 2017 · Declared Dead · 🏛 International Conference on Algorithmic Learning Theory
"No code URL or promise found in abstract"
Evidence collected by the PWNC Scanner
Authors
Jialei Wang, Weiran Wang, Dan Garber, Nathan Srebro
arXiv ID
1702.07834
Category
math.NA: Numerical Analysis
Cross-listed
cs.LG,
stat.ML
Citations
16
Venue
International Conference on Algorithmic Learning Theory
Last Checked
1 month ago
Abstract
We develop and analyze efficient "coordinate-wise" methods for finding the leading eigenvector, where each step involves only a vector-vector product. We establish global convergence with overall runtime guarantees that are at least as good as Lanczos's method and dominate it for slowly decaying spectrum. Our methods are based on combining a shift-and-invert approach with coordinate-wise algorithms for linear regression.
Community Contributions
Found the code? Know the venue? Think something is wrong? Let us know!
📜 Similar Papers
In the same crypt — Numerical Analysis
R.I.P.
👻
Ghosted
Deep learning-based numerical methods for high-dimensional parabolic partial differential equations and backward stochastic differential equations
R.I.P.
👻
Ghosted
PDE-Net: Learning PDEs from Data
R.I.P.
👻
Ghosted
Efficient tensor completion for color image and video recovery: Low-rank tensor train
R.I.P.
👻
Ghosted
Tensor Ring Decomposition
R.I.P.
👻
Ghosted
Machine learning approximation algorithms for high-dimensional fully nonlinear partial differential equations and second-order backward stochastic differential equations
Died the same way — 👻 Ghosted
R.I.P.
👻
Ghosted
Language Models are Few-Shot Learners
R.I.P.
👻
Ghosted
PyTorch: An Imperative Style, High-Performance Deep Learning Library
R.I.P.
👻
Ghosted
XGBoost: A Scalable Tree Boosting System
R.I.P.
👻
Ghosted