SupSplitLog achieves Õ(√(dT)) regret for logistic bandits without context diversity assumptions by splitting samples for an initial estimator and Newton correction, and can adapt to data-dependent bounds.
Generalized kernelized bandits: A novel self-normalized bernstein-like dimension-free inequality and regret bounds.arXiv preprint arXiv:2508.01681
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Logistic Bandits with $\tilde{O}(\sqrt{dT})$ Regret without Context Diversity Assumptions
SupSplitLog achieves Õ(√(dT)) regret for logistic bandits without context diversity assumptions by splitting samples for an initial estimator and Newton correction, and can adapt to data-dependent bounds.