EasyDeepLearn

When is step decay still appropriate?

easy

Answer

  • Multiply LR by a factor (e.g., 0.1) at fixed milestones (e.g., 60/90 epochs on ImageNet).
  • Simple, deterministic, well-understood — classic recipe for training ResNet-style CNNs with SGD+momentum.
  • Downsides: sudden LR jumps interact poorly with running momentum, need careful tuning of milestones.
  • Cosine is smoother but step decay is fine for well-studied recipes.
Check yourself — multiple choice
  • Step decay is smooth
  • Multiply LR by a factor at fixed milestones — classic ResNet recipe; simple but has sudden jumps
  • Step decay uses cosine internally
  • Only for transformers

Step decay: LR × factor at milestones — classic ResNet recipe.

#schedules#learning-rate

Practise Deep Learning

214 interview questions in this topic.

Related questions