Krylov subspace acceleration for first-order methods on convex QPs outperforms Anderson acceleration in iterations and often runtime by avoiding ill-conditioning during slow convergence.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2025 2verdicts
UNVERDICTED 2representative citing papers
The work derives an approximate local secrecy capacity and defines secret local contraction coefficients as largest generalized eigenvalues of channel matrix pencils, obtained via local Euclidean geometry approximations to the wiretap channel optimization problem.
citing papers explorer
-
Krylov Subspace Acceleration for First-Order Splitting Methods in Convex Quadratic Programming
Krylov subspace acceleration for first-order methods on convex QPs outperforms Anderson acceleration in iterations and often runtime by avoiding ill-conditioning during slow convergence.
-
Local Information-Theoretic Security via Euclidean Geometry
The work derives an approximate local secrecy capacity and defines secret local contraction coefficients as largest generalized eigenvalues of channel matrix pencils, obtained via local Euclidean geometry approximations to the wiretap channel optimization problem.