Large deviations for the perceptron model and consequences for active learning
This work addresses active learning efficiency for scenarios with expensive labeling, though it appears incremental as it builds on existing replica methods and teacher network assumptions.
The paper tackles the problem of selecting which samples to label in active learning when data is abundant but labeling is costly, by analyzing large deviations for accuracy using replica methods and showing that simple message-passing algorithms can approach optimal performance boundaries.
Active learning is a branch of machine learning that deals with problems where unlabeled data is abundant yet obtaining labels is expensive. The learning algorithm has the possibility of querying a limited number of samples to obtain the corresponding labels, subsequently used for supervised learning. In this work, we consider the task of choosing the subset of samples to be labeled from a fixed finite pool of samples. We assume the pool of samples to be a random matrix and the ground truth labels to be generated by a single-layer teacher random neural network. We employ replica methods to analyze the large deviations for the accuracy achieved after supervised learning on a subset of the original pool. These large deviations then provide optimal achievable performance boundaries for any active learning algorithm. We show that the optimal learning performance can be efficiently approached by simple message-passing active learning algorithms. We also provide a comparison with the performance of some other popular active learning strategies.