English

Open Problem: Tight Bounds for Kernelized Multi-Armed Bandits with Bernoulli Rewards

Machine Learning 2024-07-10 v1 Machine Learning

Abstract

We consider Kernelized Bandits (KBs) to optimize a function f:X[0,1]f : \mathcal{X} \rightarrow [0,1] belonging to the Reproducing Kernel Hilbert Space (RKHS) Hk\mathcal{H}_k. Mainstream works on kernelized bandits focus on a subgaussian noise model in which observations of the form f(xt)+ϵtf(\mathbf{x}_t)+\epsilon_t, being ϵt\epsilon_t a subgaussian noise, are available (Chowdhury and Gopalan, 2017). Differently, we focus on the case in which we observe realizations ytBer(f(xt))y_t \sim \text{Ber}(f(\mathbf{x}_t)) sampled from a Bernoulli distribution with parameter f(xt)f(\mathbf{x}_t). While the Bernoulli model has been investigated successfully in multi-armed bandits (Garivier and Capp\'e, 2011), logistic bandits (Faury et al., 2022), bandits in metric spaces (Magureanu et al., 2014), it remains an open question whether tight results can be obtained for KBs. This paper aims to draw the attention of the online learning community to this open problem.

Keywords

Cite

@article{arxiv.2407.06321,
  title  = {Open Problem: Tight Bounds for Kernelized Multi-Armed Bandits with Bernoulli Rewards},
  author = {Marco Mussi and Simone Drago and Alberto Maria Metelli},
  journal= {arXiv preprint arXiv:2407.06321},
  year   = {2024}
}
R2 v1 2026-06-28T17:33:29.394Z