Provably and Practically Efficient Neural Contextual Bandits

2022/05/31 by Sudeep Salgia, Salgia, Sudeep, Sattar Vakili +3 · 1 citation
Computer Science · Physics and Astronomy · #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Machine Learning and ELM #Model Reduction and Neural Networks #Neural Networks and Applications

paper · pdf · doi:10.48550/arxiv.2206.00099

openalex publication_date 2022/05/31 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

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.

Cited by

• Provable Anytime Ensemble Sampling Algorithms in Nonlinear Contextual Bandits

Related

• Learning Neural Contextual Bandits Through Perturbed Rewards
• Neural Contextual Bandits without Regret
• Uniform Generalization Bounds for Overparameterized Neural Networks
• Neural Contextual Bandits with Deep Representation and Shallow Exploration
• Neural Contextual Bandits with UCB-based Exploration