Md. Asif Uddin

Chapter VIII

Training Deep Models

Turning an architecture into a model that has learned something.

What this chapter covers

  • Dataset
  • Batch
  • Epoch
  • Optimisation
  • Learning-rate schedules
  • Weight decay
  • Gradient clipping
  • Mixed precision
  • Checkpoints
  • Evaluation

Propositions

  1. Prop. 1The batch size is a statement about gradient noise, not only about speed.A batch gradient is an estimate of the true one, with variance falling as one over the batch size. Choosing a batch is choosing how noisy each step is, and the noise is not purely a defect.
  2. Prop. 2A schedule is tuned to a step count, and does not survive being copied.The learning rate rises because the optimiser starts with no statistics and falls because a large step near the end discards what the earlier ones found. Both parts depend on the total budget.
  3. Prop. 3Weight decay and gradient clipping guard different failures and do not substitute for each other.Clipping bounds the size of a step and does nothing on almost every one. Decay pulls every parameter toward zero on every step. One is about the update, the other about where the parameters end up.
  4. Prop. 4Mixed precision is a question of range before it is a question of speed.Half precision has ample precision and a narrow exponent. Small gradients fall through its floor and round to zero, which is what loss scaling exists to prevent.
  5. Prop. 5A number means what the split lets it mean.The unit of the split has to be the unit the claim is about. Split below that unit and the held-out score measures recall of things already seen, however carefully everything else was done.