Py-BOBYQA is a Python implementation of Powell‘s BOBYQA (original paper and code). It is a derivative-free solver for general objective minimization, with optional bound constraints.

It also includes a number of features originally from DFO-LS, which improve its flexibility and robustness to noise. The documentation for Py-BOBYQA is here.

A version of Py-BOBYQA is also available in the commercial NAG Library.

Lindon Roberts

My research is in numerical analysis, particularly nonconvex and derivative-free optimization.