Cooperative multiplayer Lipschitz bandits with an unknown Lipschitz constant achieve T^(Md+1)/(Md+2)-scale regret in three information structures, with dithering synchronizing the players' discretizations.
Lipschitz Bandits without the Lipschitz Constant
1 Pith paper cite this work. Polarity classification is still indexing.
abstract
We consider the setting of stochastic bandit problems with a continuum of arms. We first point out that the strategies considered so far in the literature only provided theoretical guarantees of the form: given some tuning parameters, the regret is small with respect to a class of environments that depends on these parameters. This is however not the right perspective, as it is the strategy that should adapt to the specific bandit environment at hand, and not the other way round. Put differently, an adaptation issue is raised. We solve it for the special case of environments whose mean-payoff functions are globally Lipschitz. More precisely, we show that the minimax optimal orders of magnitude $L^{d/(d+2)} \, T^{(d+1)/(d+2)}$ of the regret bound against an environment $f$ with Lipschitz constant $L$ over $T$ time instances can be achieved without knowing $L$ or $T$ in advance. This is in contrast to all previously known strategies, which require to some extent the knowledge of $L$ to achieve this performance guarantee.
citation-role summary
citation-polarity summary
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1roles
method 1polarities
use method 1representative citing papers
citing papers explorer
-
Coordinating the Unknown Lipschitz Constant in Multiplayer Bandits
Cooperative multiplayer Lipschitz bandits with an unknown Lipschitz constant achieve T^(Md+1)/(Md+2)-scale regret in three information structures, with dithering synchronizing the players' discretizations.