COMPASS-Hedge is presented as the first parameter-free full-information anytime algorithm that simultaneously delivers minimax-optimal adversarial regret, instance-optimal stochastic regret, and Õ(1) regret to a baseline policy.
The best of both worlds: Stochastic and adversarial bandits
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
-
Learning Safely Without Knowing the World:COMPASS-Hedge
COMPASS-Hedge is presented as the first parameter-free full-information anytime algorithm that simultaneously delivers minimax-optimal adversarial regret, instance-optimal stochastic regret, and Õ(1) regret to a baseline policy.