{
  "id": "train-softmax-blobs",
  "title": "Train softmax regression on four blobs",
  "kind": "train",
  "summary": "Train multinomial logistic regression with gradient descent to reach a held-out accuracy and log loss target on four Gaussian blobs.",
  "difficulty": "easy",
  "tags": [
    "softmax",
    "logistic-regression",
    "gradient-descent",
    "log-loss"
  ],
  "lesson": "phases/02-ml-fundamentals/03-logistic-regression",
  "cheatsheet": "classical-ml",
  "minutes": 25,
  "entry": [
    "train",
    "predict_proba"
  ],
  "collections": [
    "train-tiny-models",
    "classical-ml"
  ],
  "time_limit_s": 15,
  "budget": {
    "steps": 500
  },
  "target": {
    "metric": "held-out log loss",
    "value": 0.11
  },
  "mutants": {
    "grad_missing_onehot": "Uses the probabilities as the error and forgets to subtract the one-hot targets.",
    "no_bias_update": "Never updates the biases, so each class keeps the same base score.",
    "no_standardize": "Trains on the raw features without the mean and std scaling, so 500 steps are not enough.",
    "no_max_shift": "Calls np.exp on the raw scores, so far points overflow and give NaN.",
    "softmax_wrong_axis": "Normalizes the exponentials over the batch axis 0 and not over the classes.",
    "standardizes_in_place": "Scales X in place with -= and /=, so the caller's array changes."
  }
}