Under SGDClassifier's 'optimal' learning-rate schedule, why can changing alpha alter more than regularization?
Classic MLLevel: AdvancedCoupled regularization and step size
Under SGDClassifier's 'optimal' learning-rate schedule, why can changing alpha alter more than regularization?
Hints
- Read the denominator of the step-size formula.
- Hyperparameters can play multiple roles.
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 — sgd · BSD-3-Clause · answer: Quantoros editorial