Why is Levenberg–Marquardt not the appropriate leastsquares method for explicit parameter bounds?
MathematicsLevel: IntermediateNonlinear least squares
Why is Levenberg–Marquardt not the appropriate least_squares method for explicit parameter bounds?
Hints
- Method capabilities differ.
- Bounds need dedicated handling.
Answer
The LM method does not support bounds. Use a bounds-capable method such as trust-region reflective and verify the returned feasible solution.
Source and licence: SciPy — nonlinear least squares · BSD-3-Clause · answer: Quantoros editorial