Timezone: »

 
Poster
Pure Exploration in Kernel and Neural Bandits
Yinglun Zhu · Dongruo Zhou · Ruoxi Jiang · Quanquan Gu · Rebecca Willett · Robert Nowak

Tue Dec 07 08:30 AM -- 10:00 AM (PST) @
in Poster Session 1 »

We study pure exploration in bandits, where the dimension of the feature representation can be much larger than the number of arms. To overcome the curse of dimensionality, we propose to adaptively embed the feature representation of each arm into a lower-dimensional space and carefully deal with the induced model misspecifications. Our approach is conceptually very different from existing works that can either only handle low-dimensional linear bandits or passively deal with model misspecifications. We showcase the application of our approach to two pure exploration settings that were previously under-studied: (1) the reward function belongs to a possibly infinite-dimensional Reproducing Kernel Hilbert Space, and (2) the reward function is nonlinear and can be approximated by neural networks. Our main results provide sample complexity guarantees that only depend on the effective dimension of the feature spaces in the kernel or neural representations. Extensive experiments conducted on both synthetic and real-world datasets demonstrate the efficacy of our methods.

Keywords: Theory · Deep Learning · Reinforcement Learning and Planning · Bandits · Representation Learning

Author Information

Yinglun Zhu (University of Wisconsin, Madison)
Dongruo Zhou (UCLA)
Ruoxi Jiang (The University of Chicago)
Quanquan Gu (UCLA)
Rebecca Willett (University of Wisconsin)
Robert Nowak (University of Wisconsion-Madison)

More from the Same Authors