mediumGoogleDatabricksScale

Walk me through SGD vs mini-batch vs Adam, learning-rate schedules, and what vanishing or exploding gradients look like in practice.

Most candidates recite the Adam update equation and stop. The interviewer wants the decision: when plain SGD with momentum still wins, why Adam is the safe default for new architectures, and how you diagnose a training run that is silently dying from a gradient that shrank to zero.

Updated Sep 2026 · Grounded in real Forward Deployed Engineer interview loops and written to a senior-engineer editorial bar.

20 answers per topic instead of 10, plus saved progress and bookmarks · no cardor unlock all 548 remaining answers · ₹2,000 / $25

Every answer, concept and course, every paper breakdown, all published video lessons, hands-on FDE Lab missions, Premium PDF guides and companion files, the full practice-test bank and work-sample downloads. Referral Premium excludes guide PDFs and their companion files.

6 months · One payment · No auto-renewal

Study alongside free video lessons.

Keep practising

Next in this trackExplain backpropagation and why deep networks can be trained at all, without writing a wall of calculus.Premium Next in this trackWhy did attention and transformers replace RNNs for sequence modeling? Explain it conceptually.Premium Next in this trackExplain CNN fundamentals (convolution, pooling, parameter sharing). When does classical computer vision still matter?Premium

FEDITOR'S NOTE

The screen is whether you treat the optimizer as a diagnostic instrument rather than a formula to memorize. The reserved follow-up is almost always 'how would you tell vanishing from exploding gradients from the logs alone' and 'why does Adam sometimes generalize worse than SGD'. Naming the gradient-norm trace and the SGD-generalizes-better finding before being asked is the senior signal.

DISCUSSION · 0

No comments yet — be the first to share your approach.