Exponential-weight algorithm attains Õ(√(T γ_T)) adversarial regret for kernelized bandits, with matching lower bounds for SE and Matérn kernels plus a Nyström-efficient variant.
Vershynin.High-dimensional probability: An introduction with applications in data science
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Nearly-Optimal Algorithm for Adversarial Kernelized Bandits
Exponential-weight algorithm attains Õ(√(T γ_T)) adversarial regret for kernelized bandits, with matching lower bounds for SE and Matérn kernels plus a Nyström-efficient variant.