Explain core ML fundamentals and tradeoffs

ML Fundamentals Interview Prompt

Answer the following ML fundamentals questions clearly and with practical examples:

1. Bias vs. variance
   • What are bias and variance?
   • How do you diagnose high bias vs high variance from train/validation curves?
   • What actions reduce bias vs reduce variance?
2. Overfitting
   • Why does overfitting happen?
   • List common mitigations for linear models and for neural networks.
3. Imbalanced data
   • Why can accuracy be misleading?
   • What metrics are better?
   • What approaches can you use at the data level, algorithm level, and thresholding level?
4. Loss functions (especially for neural networks)
   • When would you use MSE vs cross-entropy vs focal loss?
   • What is label smoothing and why might it help?
5. Optimization
   • Compare SGD, Momentum, Adam.
   • What are learning-rate schedules and why do they matter?
   • What problems do vanishing/exploding gradients cause and how do you address them?
6. Neural network architectures (high level)
   • When would you prefer CNNs, RNNs, Transformers?
   • What are common regularization techniques (dropout, weight decay, batch norm) and how do they work?

Assume a product ML setting (recommendation/ranking/classification).