The 60-second answer
Gradient descent follows the negative loss gradient; SGD/mini-batch methods trade exact gradients for scalable noisy estimates. Adam adds adaptive first/second moments; SGD can generalize strongly with appropriate momentum and schedules.
Build the answer in this order
Gradient descent follows the negative loss gradient; SGD/mini-batch methods trade exact gradients for scalable noisy estimates.
Adam adds adaptive first/second moments; SGD can generalize strongly with appropriate momentum and schedules.
Learning rate is central: use warmup/decay or plateau schedules and diagnose divergence, noisy updates, exploding gradients, and plateaus.
Compare convergence, optimizer-state memory, batch size, and distributed-training cost.
A useful interview mental model
This is the shape of a strong answer—not a script to memorize.
Senior-level signal
- Relate optimizer and schedule to effective batch/token budget and gradient-noise scale.
- For large models, optimizer-state memory and communication can dominate the theoretical convergence discussion.
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.