Neural Active Learning with Performance Guarantees
This work addresses efficient label acquisition in streaming data for machine learning, but it is incremental as it builds on existing NTK tools and active learning frameworks.
The paper tackles active learning in streaming non-parametric regimes without assumptions on labeling functions, using Neural Tangent Kernel approximations to derive an algorithm with joint guarantees on cumulative regret and label requests, recovering minimax results in linear cases.
We investigate the problem of active learning in the streaming setting in non-parametric regimes, where the labels are stochastically generated from a class of functions on which we make no assumptions whatsoever. We rely on recently proposed Neural Tangent Kernel (NTK) approximation tools to construct a suitable neural embedding that determines the feature space the algorithm operates on and the learned model computed atop. Since the shape of the label requesting threshold is tightly related to the complexity of the function to be learned, which is a-priori unknown, we also derive a version of the algorithm which is agnostic to any prior knowledge. This algorithm relies on a regret balancing scheme to solve the resulting online model selection problem, and is computationally efficient. We prove joint guarantees on the cumulative regret and number of requested labels which depend on the complexity of the labeling function at hand. In the linear case, these guarantees recover known minimax results of the generalization error as a function of the label complexity in a standard statistical learning setting.