The 60-second answer
First rule out leakage or train/validation distribution mismatch; “overfitting” is not always excessive model capacity. Compare learning curves, slices, label quality, and repeated splits before changing the model.
Build the answer in this order
First rule out leakage or train/validation distribution mismatch; “overfitting” is not always excessive model capacity.
Compare learning curves, slices, label quality, and repeated splits before changing the model.
Remedies include more/better data, augmentation, reduced capacity, early stopping, weight decay/dropout, feature cleanup, and stronger validation protocol.
Re-run a simple baseline after each major change so complexity is justified by reproducible validation gain.
A useful interview mental model
This is the shape of a strong answer—not a script to memorize.
Senior-level signal
- Senior answers distinguish variance from leakage, temporal drift, and selection bias before prescribing regularization.
- Discuss how repeated tuning on one validation set can itself overfit the evaluation process.
What the interviewer is really testing
Likely follow-up questions
Common weak-answer patterns
- Reciting a definition without mechanism or assumptions.
- Claiming one technique is always better without a data regime.
- Stopping before failure modes, validation, or deployment implications.