Develops auxiliary gradient-flow solvers that shift nonlinearity in N-function governed variational problems to an auxiliary variable, with metric-space convergence proofs for p-Laplacian and p-Stokes in 4/3 ≤ p ≤ 4 and practical discretizations outperforming Newton in tests.
An introduction to the analysis of gradients systems.arXiv preprint arXiv:2306.05026, 2023
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Establishes Riemannian gradient flow equivalence for neural MMS steps, linear convergence under convexity conditions, and O(δ) tracking bounds for inexact iterates.
citing papers explorer
-
Auxiliary Gradient-Flow Solvers for Generalized Newtonian Models
Develops auxiliary gradient-flow solvers that shift nonlinearity in N-function governed variational problems to an auxiliary variable, with metric-space convergence proofs for p-Laplacian and p-Stokes in 4/3 ≤ p ≤ 4 and practical discretizations outperforming Newton in tests.
-
Global Convergence and Error Propagation in Neural Gradient Flows: A Riemannian Optimization Framework
Establishes Riemannian gradient flow equivalence for neural MMS steps, linear convergence under convexity conditions, and O(δ) tracking bounds for inexact iterates.