DeepAI AI Chat
Log In Sign Up

Neural Contextual Bandits without Regret

by   Parnian Kassraie, et al.

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 γ_T, a complexity parameter capturing the difficulty of learning. Our bounds on γ_T 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 𝒪̃(T^-1/2d) rate, where d is the dimension of the context.


page 1

page 2

page 3

page 4


Smooth Contextual Bandits: Bridging the Parametric and Non-differentiable Regret Regimes

We study a nonparametric contextual bandit problem where the expected re...

Graph Neural Network Bandits

We consider the bandit optimization problem with the reward function def...

Regret Minimization in Isotonic, Heavy-Tailed Contextual Bandits via Adaptive Confidence Bands

In this paper we initiate a study of non parametric contextual bandits u...

Provably and Practically Efficient Neural Contextual Bandits

We consider the neural contextual bandit problem. In contrast to the exi...

Making the most of your day: online learning for optimal allocation of time

We study online learning for optimal allocation when the resource to be ...

An Empirical Study of Neural Kernel Bandits

Neural bandits have enabled practitioners to operate efficiently on prob...

Improved Algorithms for Multi-period Multi-class Packing Problems with Bandit Feedback

We consider the linear contextual multi-class multi-period packing probl...