Nonlinear splitting of gradients and constraints yields semi-implicit gradient methods and cheaper adjoint gradients, demonstrated on nonconvex benchmarks, quantum tomography, and kinetic transport.
Chung, and John C
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.OC 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Nonlinear Splitting for Gradient-Based Unconstrained and Adjoint Optimization
Nonlinear splitting of gradients and constraints yields semi-implicit gradient methods and cheaper adjoint gradients, demonstrated on nonconvex benchmarks, quantum tomography, and kinetic transport.