Provably and Practically Efficient Neural Contextual Bandits
Machine Learning
2022-06-02 v1 Machine Learning
Abstract
We consider the neural contextual bandit problem. In contrast to the existing work which primarily focuses on ReLU neural nets, we consider a general set of smooth activation functions. Under this more general setting, (i) we derive non-asymptotic error bounds on the difference between an overparameterized neural net and its corresponding neural tangent kernel, (ii) we propose an algorithm with a provably sublinear regret bound that is also efficient in the finite regime as demonstrated by empirical studies. The non-asymptotic error bounds may be of broader interest as a tool to establish the relation between the smoothness of the activation functions in neural contextual bandits and the smoothness of the kernels in kernel bandits.
Cite
@article{arxiv.2206.00099,
title = {Provably and Practically Efficient Neural Contextual Bandits},
author = {Sudeep Salgia and Sattar Vakili and Qing Zhao},
journal= {arXiv preprint arXiv:2206.00099},
year = {2022}
}