Interactive demo · Probabilistic Machine Learning · Chapter 19

Active learning: which label to buy next

A pool of 300 unlabeled points, two of them labeled to start. A Bayesian logistic regression (Laplace posterior on RBF features) is refitted after every query. Three rules choose the next point: random; maximum entropy, the point whose predicted label is most uncertain; and BALD, the point whose label would tell us most about the parameters, the predictive entropy minus the average entropy given the parameters (19.51). Left: the predictive probability, the pool (dot size grows with the chosen rule's score) and the next query (gold ring). Right: test accuracy of the three rules from the same start. In the second data set a patch of points has labels that are pure coin flips, which look uncertain to every model but carry no information about the boundary.

Pool

Rule shown on the left

Queries made q

Starting pair

Try these

Data: two moons (noise 0.25), 300 pool points and 1000 test points, simulated. The second pool has 200 moons points (noise 0.12) plus 100 points in a Gaussian patch around (1, 0.25) with random labels; its test set is 1000 clean moons points. Model: logistic regression on a fixed 7 by 5 grid of Gaussian features, prior N(0, I), Laplace posterior; predictive probability sigmoid(m / sqrt(1 + πs2/8)) where m and s2 are the mean and variance of the logit. BALD uses a closed-form approximation of the expected entropy (within 0.03 nats of Monte Carlo). “Random” follows a fixed random order of the pool for each starting pair.

In the lecture notes