Nonparametric adaptive active learning under local smoothness condition
This work addresses the challenge of expensive labeling in active learning by providing a more flexible and adaptive approach, though it is incremental as it builds on existing non-adaptive algorithms.
The paper tackles the problem of adaptive active learning in a nonparametric setting by developing a novel algorithm that works under more general assumptions and adapts to parameters, avoiding exclusions like Gaussian densities, and achieves a minimax rate of convergence.
Active learning is typically used to label data, when the labeling process is expensive. Several active learning algorithms have been theoretically proved to perform better than their passive counterpart. However, these algorithms rely on some assumptions, which themselves contain some specific parameters. This paper adresses the problem of adaptive active learning in a nonparametric setting with minimal assumptions. We present a novel algorithm that is valid under more general assumptions than the previously known algorithms, and that can moreover adapt to the parameters used in these assumptions. This allows us to work with a larger class of distributions, thereby avoiding to exclude important densities like gaussians. Our algorithm achieves a minimax rate of convergence, and therefore performs almost as well as the best known non-adaptive algorithms.