EasyDeepLearn

What is scheduled sampling?

medium

Answer

  • Interpolate between teacher forcing and self-generation during training: with probability p feed the true token, with 1-p feed the model's own prediction.
  • Decay p over training (start at 1, end near 0).
  • Bridges the train/inference gap without full exposure.
  • Works OK for RNN seq2seq but doesn't compose easily with parallel transformer training (which processes all positions at once).
Check yourself — multiple choice
  • Always uses true tokens
  • Mix teacher-forced and self-generated inputs with a probability that decays over training
  • Only for classification
  • Requires no schedule

Scheduled sampling: gradually replace ground truth with model outputs during training.

#training#rnn

Practise Deep Learning

214 interview questions in this topic.

Related questions