Timezone: »

 
Poster
Neural Active Learning with Performance Guarantees
Zhilei Wang · Pranjal Awasthi · Christoph Dann · Ayush Sekhari · Claudio Gentile

Wed Dec 08 04:30 PM -- 06:00 PM (PST) @ Virtual
in Poster Session 4 »

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.

Keywords: Deep Learning · Active Learning

Author Information

Zhilei Wang (NYU Courant)
Pranjal Awasthi (Google)
Christoph Dann (Google Research)
Ayush Sekhari (Cornell University)
Claudio Gentile (Google Research)

More from the Same Authors