The paper claims a near-optimal regret bound for cross-learning contextual bandits with graphical feedback, but the theorem as stated is not supported for graphs without self-loops, per the paper's own conclusion.
By the previous two lemmas, it is easy to see that Pr(Q)≥ 1− 3K(T /L) exp(−ι)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Nearly Tight Bounds for Cross-Learning Contextual Bandits with Graphical Feedback
The paper claims a near-optimal regret bound for cross-learning contextual bandits with graphical feedback, but the theorem as stated is not supported for graphs without self-loops, per the paper's own conclusion.