UniCLUB and PhaseUniCLUB add uniform exploration to clustering of bandits, removing sub-Gaussian context assumptions while keeping O(d sqrt(mT) log T) regret, plus a smoothed adversarial setting with a proof gap.
Second workshop on information heterogeneity and fusion in recommender systems (hetrec2011)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Demystifying Online Clustering of Bandits: Enhanced Exploration Under Stochastic and Smoothed Adversarial Contexts
UniCLUB and PhaseUniCLUB add uniform exploration to clustering of bandits, removing sub-Gaussian context assumptions while keeping O(d sqrt(mT) log T) regret, plus a smoothed adversarial setting with a proof gap.