Neural Contextual Bandits without Regret


METADATA ONLY
Loading...

Date

2022

Publication Type

Conference Paper

ETH Bibliography

yes

Citations

Altmetric
METADATA ONLY

Data

Rights / License

Abstract

Contextual bandits are a rich model for sequential decision making given side information, with important applications, e.g., in recommender systems. We propose novel algorithms for contextual bandits harnessing neural networks to approximate the unknown reward function. We resolve the open problem of proving sublinear regret bounds in this setting for general context sequences, considering both fully-connected and convolutional networks. To this end, we first analyze NTK-UCB, a kernelized bandit optimization algorithm employing the Neural Tangent Kernel (NTK), and bound its regret in terms of the NTK maximum information gain γT, a complexity parameter capturing the difficulty of learning. Our bounds on γT for the NTK may be of independent interest. We then introduce our neural network based algorithm NN-UCB, and show that its regret closely tracks that of NTK-UCB. Under broad non-parametric assumptions about the reward function, our approach converges to the optimal policy at a O~(T−1/2d) rate, where d is the dimension of the context.

Publication status

published

Book title

Proceedings of The 25th International Conference on Artificial Intelligence and Statistics

Journal / series

Volume

151

Pages / Article No.

240 - 278

Publisher

PMLR

Event

25th International Conference on Artificial Intelligence and Statistics (AISTATS 2022)

Edition / version

Methods

Software

Geographic location

Date collected

Date created

Subject

Organisational unit

03908 - Krause, Andreas / Krause, Andreas check_circle

Notes

Funding

815943 - Reliable Data-Driven Decision Making in Cyber-Physical Systems (EC)

Related publications and datasets