pith. sign in

12 A Replicable Multi Armed Bandit Proof Theorem3.1Consider RepUCB (Algorithm

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.LG 1

years

2026 1

verdicts

CONDITIONAL 1

representative citing papers

Replicable Bandits with UCB based Exploration

cs.LG · 2026-04-21 · conditional · novelty 7.0

RepUCB and RepLinUCB deliver replicable regret bounds O(K² log²T / ρ² ⋅ sum) for MAB and Õ((d + d³/ρ)√T) for linear bandits, improving the prior best by O(d/ρ) via optimistic exploration and a new replicable ridge estimator.

citing papers explorer

Showing 1 of 1 citing paper.

  • Replicable Bandits with UCB based Exploration cs.LG · 2026-04-21 · conditional · none · ref 15

    RepUCB and RepLinUCB deliver replicable regret bounds O(K² log²T / ρ² ⋅ sum) for MAB and Õ((d + d³/ρ)√T) for linear bandits, improving the prior best by O(d/ρ) via optimistic exploration and a new replicable ridge estimator.