NL-RMM-GKS extends majorization-minimization and Krylov subspace recycling to nonlinear inverse problems with uncertain forward operators, offering alternating minimization, variable projection, and streaming variants for dynamic imaging.
Title resolution pending
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
math.NA 3years
2026 3representative citing papers
EDA-specific RHS differences used as sketching matrix for randomized Hessian preconditioner accelerate linear solves across the ensemble in Lorenz-96 experiments.
Model order reduction with snapshots from high-fidelity or one-shot solves accelerates 3D thermal topology optimization by up to 16x versus standard high-fidelity workflows and 1.54x versus one-shot alone.
citing papers explorer
-
Nonlinear RMM-GKS for Large-Scale Dynamic and Streaming Inverse Problems with Uncertain Forward Operators
NL-RMM-GKS extends majorization-minimization and Krylov subspace recycling to nonlinear inverse problems with uncertain forward operators, offering alternating minimization, variable projection, and streaming variants for dynamic imaging.
-
Accelerating an ensemble of variational data assimilations with randomized preconditioning
EDA-specific RHS differences used as sketching matrix for randomized Hessian preconditioner accelerate linear solves across the ensemble in Lorenz-96 experiments.
-
Comparison of model order reduction techniques with one-shot procedure for topology optimization for thermal applications
Model order reduction with snapshots from high-fidelity or one-shot solves accelerates 3D thermal topology optimization by up to 16x versus standard high-fidelity workflows and 1.54x versus one-shot alone.