55What is a validation set for, and how do you use it during training without overfitting to it?▼easyGoogleDatabricksMicrosoft1 replies◆ premiumThe validation set is the one you tune and select on; the test set is the one you only look at once. Confusing them, or tuning so hard you overfit the validation set, is how a model that aced offline metrics dies in production.Open full answer →
66How do you tune hyperparameters efficiently?▼mediumGoogleAmazonDatabricks1 replies◆ premiumGrid search is the answer that signals you have never paid for compute. The efficient answer is random or Bayesian over a small set of parameters that actually move the metric, with Hyperband killing bad runs early, on a validation set you never let leak.Open full answer →
