EasyDeepLearn

How does batch size affect training dynamics?

medium

Answer

  • Larger batch → lower gradient noise, closer to true gradient, allows higher learning rate (roughly LR ∝ sqrt(batch)).
  • But too large batches tend to converge to sharper minima that generalize slightly worse (the 'generalization gap').
  • Small batches are noisier — regularizing effect that often helps final accuracy.
  • Rule: scale LR with batch and use warmup to keep training stable at very large batches (LARS/LAMB for extreme scales).
Check yourself — multiple choice
  • Batch size has no effect on generalization
  • Larger batch = less noise, higher LR allowed, but tends toward sharper minima and slightly worse generalization
  • Smaller batch is always faster
  • Batch size only affects memory

Batch controls noise ⇒ scale LR + warmup; watch generalization gap at extreme batch.

#training#batch-size#learning-rate

Practise Deep Learning

214 interview questions in this topic.

Related questions