Pure Exploration in Kernel and Neural Bandits
arXiv:2106.12034
Abstract
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 misspecification. Our approach is conceptually very different from existing works that can either only handle low-dimensional linear bandits or passively deal with model misspecification. 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.
References in corpus (10)
- On Exact Computation with an Infinitely Wide Neural Net
- Generalization Bounds of Stochastic Gradient Descent for Wide and Deep Neural Networks
- Best-Arm Identification in Linear Bandits
- Spectral bandits for smooth graph functions
- Gamification of Pure Exploration for Linear Bandits
- Adapting to Misspecification in Contextual Bandits
- An Empirical Process Approach to the Union Bound: Practical Algorithms for Combinatorial and Linear Bandits
- The True Sample Complexity of Identifying Good Arms
- Finding All ε-Good Arms in Stochastic Bandits
- High-Dimensional Experimental Design and Kernel Bandits