Why can mutating the training array after fitting an SVC with a callable kernel change later behavior unexpectedly?
Classic MLLevel: AdvancedTraining reference lifetime
Why can mutating the training array after fitting an SVC with a callable kernel change later behavior unexpectedly?
Hints
- Check ownership, not only fitted coefficients.
- Inference may still consult training inputs.
Answer
This answer is part of mentoring
Advanced questions come with a full breakdown and a mock interview with a working quant researcher. The first call is free.
Source and licence: scikit-learn 1.7.2 — svm · BSD-3-Clause · answer: Quantoros editorial